Alle afleveringen
224 afleveringen, van nieuw naar oud
-
Can Neural Networks Replace MCMC?
26 oktober 2026 · 4 min
Today’s clip is from Episode 167 of Learning Bayesian Statistics, featuring Paul-Christian Bürkner and Steve Bronder, recorded live at StanCon 2026 in Uppsala, Sweden. Lees meer
Paul Bürkner, creator of brms and a leading researcher behind BayesFlow, explains how neural networks can replace MCMC for Bayesian inference. Instead of evaluating likelihood and prior densities, the networks are trained on simulated data, so you can do simulation-based inference (SBI) even when the likelihood is intractable. Once trained, they give you amortized, real-time posteriors for new datasets, and they have made SBI scalable well beyond what approximate Bayesian computation could handle.
Paul is also candid about the limits. Neural methods come with unstable training and no guarantees, and they can be unreliable on out-of-distribution or misspecified data, which is why MCMC is still the more trustworthy option wherever you can apply it. He ends with how his group is building diagnostics to flag when a neural posterior can’t be trusted.
Full discussion here
Support & Resources
→ Support the show on Patreon
→ Bayesian Modeling Course (first 2 lessons free):
Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work! -
#167 Amortized Inference & GPUs for Stan, with Paul-Christian Bürkner & Steve Bronder
20 oktober 2026 · 1 uur 3 min
Support & Resources
→ Support the show on Patreon
→ Bayesian Modeling Course (first 2 lessons free) Lees meerOur theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work!
Takeaways:
Q: What is amortized Bayesian inference and how does it differ from MCMC?
Instead of running MCMC on each dataset, you train neural networks on data simulated from the model, so you don't need likelihood or prior densities. Once training is done, inference on a new dataset is essentially instant: new data in, posterior out. The price is everything neural networks bring with them, from unstable training to a lack of guarantees. Paul's stated goal is to make these methods as reliable and robust as MCMC while staying orders of magnitude faster, and he's candid that he doesn't know whether the field will ever get there.
Q: Why would a Bayesian model not have a usable likelihood?
A: Usually not because the likelihood can't be written down in principle, but because computing it is so expensive or numerically unstable that it's intractable in practice. Paul gives two cases. First, mechanistic models built on complicated differential equations, as in physical chemistry or biology, where you can't solve through the equations to get densities and gradients in a stable, fast way. Second, big latent variable models with thousands of latent variables between the parameters and the data, where marginalizing them out is hopeless. In both cases, simulating from the model is easy: simulate the parameters, the latents and the data, throw the latents away, and learn the relation between parameters and data from the simulations.
Full takeaways here!
Chapters:
15:33 What is amortized Bayesian inference and when should you use it instead of MCMC?
23:18 Why would a Bayesian model not have a usable likelihood?
26:03 What's holding back GPU computing in Stan?
31:14 What are sum-to-zero constraints and why do they make models sample faster?
35:55 What is a Jacobi… -
What Do Kernels, Length Scale & Amplitude Mean in Gaussian Processes?
7 oktober 2026 · 4 min
Today's clip is from Episode 166, featuring Bill Engels & Jesse Grabowski. In this conversation, Bill explains what a kernel means in a Gaussian process and how it defines the idea of similarity between data points. He then breaks down the role of the length scale, showing how it controls how quickly the relationship between two points changes, and how amplitude controls the overall scale of the functions a GP can represent. Lees meer
The discussion also connects these ideas to the practical use of Gaussian processes for modeling unknown nonlinear relationships, and why kernels provide an interpretable way to describe how inputs are related.
Full discussion here
Support & Resources
→ Support the show on Patreon
→ Bayesian Modeling Course (first 2 lessons free):
Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work! -
#166 PTGP: A New Gaussian Process Library, with Bill Engels & Jesse Grabowski
1 oktober 2026 · 1 uur 58 min
Support & Resources
→ Support the show on Patreon
→ Bayesian Modeling Course (first 2 lessons free) Lees meerOur theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work!
Takeaways:
Q: What is PTGP and why did Bill and Jesse build it?
A: PTGP is a new Gaussian process library built on PyTensor and PyMC, aimed squarely at practitioners rather than researchers assembling their own GP methods from papers. Bill Engels, who wrote PyMC's original GP submodule during a Google Summer of Code, built it because most GP libraries implement one method well but give little guidance on when to use it or how to fix it when it breaks. PTGP is opinionated by design: it picks battle-tested algorithms, tells you which one fits your data size, and ships the debugging knowledge alongside the code.Q: Why are Gaussian processes described as sitting at the intersection of statistics and machine learning?
A: A Gaussian process starts from a simple idea: things that are close in the input space should be close in the output space, and the kernel function defines exactly what "close" means for your problem. That makes GPs look like machine learning (let the data speak through a flexible function) while staying fully interpretable once you've chosen a kernel, since observing data collapses the process into an ordinary multivariate normal.Full takeaways here!
Chapters:
05:51 Where do Gaussian processes actually get used in practice?
09:07 What do a kernel's length scale and amplitude actually control?
11:58 What is HSGP and how does it combine with hierarchical models?14:51 Where does PTGP fit in a modern data science workflow?
21:01 Are Gaussian processes interpretable, or are they a black box?27:49 Why aren't Gaussian processes used everywhere already?
32:44 What does a kernel function actually tell you about your data?46:33 What is PyTensor and what does it give you over other backends?50:54 How do you build a Gaussian process model in PyTen… -
How AI Can Evaluate Bayesian Workflows with Bayesify
28 september 2026 · 5 min
Today's clip is from Episode 165, featuring Alex Fengler. In this conversation, Alex introduces Bayesify , a tool that uses AI to analyze research papers and assess how well they follow a Bayesian workflow. Lees meer
He explains how the tool breaks an analysis down step by step, identifies strengths and weaknesses, and provides suggestions for improving the paper. They also discuss how BasiFi can be used as an educational resource, a review engine for researchers, and potentially as a way to study how the quality of Bayesian analyses has changed over time.
Alex also explains why the team is building a human-rated "gold set" of papers to evaluate how well the tool's scoring aligns with expert judgment. It's an interesting example of how AI can be used not just to generate research, but to help verify and evaluate statistical workflows.
Full discussion here
Support & Resources
→ Support the show on Patreon
→ Bayesian Modeling Course (first 2 lessons free):
Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work! -
#165 Hierarchical Sequential Sampling Modeling, with Alex Fengler
18 september 2026 · 1 uur 48 min
Support & Resources
→ Support the show on Patreon
→ Bayesian Modeling Course (first 2 lessons free) Lees meerOur theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work!
Takeaways:
Q: What is HSSM and how does it relate to HDDM?
A: HSSM stands for hierarchical sequential sampling models, a generalization of HDDM (hierarchical drift diffusion models), the older toolbox for the same class of decision-making models, but HSSM is built from the ground up on simulation-based inference. That's what lets it handle any variation of the underlying process model, not just the ones with a tractable closed-form likelihood.Q: What is the drift diffusion model and why has cognitive science relied on it so heavily?
A: The drift diffusion model treats a decision as a random walk that accumulates evidence until it crosses one of two boundaries, with parameters controlling boundary separation, starting bias, and drift rate. It's been used in thousands of published papers largely because it has a closed-form likelihood, which makes standard Bayesian and maximum-likelihood inference fast. Small variations on the model are often just as scientifically motivated, but if their likelihoods aren't analytically convenient, the literature using them stays sparse.Q: What is a likelihood approximation network (LAN) and what does it actually learn?
A: A LAN is a neural network trained to take in a process's parameters and a trial's outcome and output how likely that outcome was, learned purely from repeated simulation rather than derived analytically. Once trained, it functions as a fast, reusable likelihood you plug directly into Bayes' rule, in place of a closed-form solution that may not exist for the model you actually want to fit.Q: What's the difference between amortizing the likelihood and amortizing the posterior?
A: Amortizing the likelihood, HSSM's approach, means training a network once to approximate the likelihood, then reusing that… -
Bayesian Principal Stratification: Modeling Treatment Effects
11 september 2026 · 5 min
Today's clip is from Episode 164, featuring Andrew Gelman, Aki Vehtari & Richard McElreath. In this conversation, Andrew explains how Bayesian principal stratification can be used to reason about treatment effects when there is an intermediate treatment or outcome that is only partially observed. Lees meer
He discusses how latent variables can represent whether someone would take a stage-two treatment, and how pre-treatment characteristics such as age, location, and past spending can help build a model for this process.
Richard connects the problem to the broader distinction between per-protocol and intent-to-treat analyses, and they discuss how standard approaches such as instrumental variables can be understood as special cases of more general Bayesian models. It's a useful example of how Bayesian modeling can represent the full process behind a causal question rather than relying on simplifying assumptions.
Full discussion here
Support & Resources
→ Support the show on Patreon
→ Bayesian Modeling Course (first 2 lessons free):
Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work! -
Why a Bayesian Workflow Goes Beyond Fitting Models
2 september 2026 · 4 min
Today's clip is from Episode 164, featuring Andrew Gelman, Aki Vehtari & Richard McElreath. In this conversation, Andrew explains why a Bayesian workflow goes far beyond simply fitting a model. Lees meer
He discusses the importance of building, fitting, and checking models, and why moving between simpler and more complicated models can reveal insights that a single model might miss.
He also explores how simulation and generative modeling can help researchers evaluate new models and gain confidence in their results, even when there isn't an established method or published study to rely on. It's a look at why good statistical practice isn't just about getting an answer, but knowing how much you can trust it.
Full discussion here
Support & Resources
→ Support the show on Patreon
→ Bayesian Modeling Course (first 2 lessons free):
Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work! -
#164 Bayesian Workflow, with Andrew Gelman, Aki Vehtari & Richard McElreath
31 augustus 2026 · 1 uur 44 min
Support & Resources
→ Support the show on Patreon
→ Bayesian Modeling Course (first 2 lessons free) Lees meerOur theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work
Takeaways:
Q: What is the "Bayesian Workflow" book about, and who is it for?A: It covers what the three authors know that isn't already in Bayesian Data Analysis (BDA3) or Statistical Rethinking, organized around case studies that walk through full analyses end to end rather than just giving a recommendation. It's not an introduction to Bayesian inference -- it assumes you already know the basics -- but a guide to making theoretically informed, professional decisions at the many branching points a real analysis involves that source books rarely acknowledge.
Q: What's a concrete way to report Bayesian results without just handing over a posterior distribution?
A: Report a few named scenarios from the distribution, such as pessimistic, median, and optimistic. This is easier to discuss than a full posterior and helps shift the conversation toward what would move outcomes from the median toward the optimistic case.
Full takeaways
Chapters:
00:18:22 What is the elevator pitch for the Bayesian Workflow book?
00:20:12 Where does workflow sit between statistical theory and case studies?
00:27:21 Why express your scientific background in a generative model?
00:36:43 How is a Bayesian workflow different from a pipeline?
00:39:03 What is reverse Bayes, and how does it help with prior sensitivity?
00:43:53 How do Bayesians reinterpret non-Bayesian methods?
00:45:02 How is the Bayesian Workflow book structured?
00:48:49 How do you model bat mortality at wind farms from zero-inflated carcass counts?
00:52:24 When does a hierarchical model stop being an innocuous assumption?
00:58:17 Can multilevel regression and poststratification pool detection across sites?
00:59:32 Why start with a big generative simulation before the statistical model?
01:02:05 What is the "se… -
Making Gaussian Processes Easier to Use
25 augustus 2026 · 5 min
Today's clip is from Episode 154, featuring Thomas Pinder. In this conversation, Thomas shares what he sees as the next steps for GPJax and how the project could become easier to use beyond its original research-focused audience. Lees meer
He discusses creating a higher-level interface that could make fitting Gaussian processes possible in just a few lines of code, while still keeping the flexibility and infrastructure that GPJax provides. He also talks about making the documentation more engaging by moving beyond synthetic examples and showcasing real-world applications, such as modeling ocean currents with Gaussian processes.
It's a look at how GPJax could evolve from a powerful research tool into something that's even more accessible and practical for a wider range of users.
Full discussion here
Support & Resources
→ Support the show on Patreon
→ Bayesian Modeling Course (first 2 lessons free):
Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work! -
The Future of Faster MCMC
21 augustus 2026 · 4 min
Today's clip is from Episode 163, featuring Eliot Carlson and Adrian Seyboldt. In this conversation, Eliot and Adrian look beyond current approaches to HMC adaptation and preconditioning and share the ideas they're most excited to explore next. Lees meer
Eliot discusses new ways of parallelizing MCMC by solving for an entire trajectory at once rather than computing every step sequentially, a potentially powerful direction for expensive, high-dimensional problems. Adrian, meanwhile, talks about exploring non-adjusting methods and going beyond first-order information by investigating how higher-order autodiff and second-order derivatives could open up new possibilities for sampling.
It's a glimpse into some of the ideas that could help make MCMC faster and more scalable as computational hardware continues to become increasingly parallel.
Full discussion here
Support & Resources
→ Support the show on Patreon
→ Bayesian Modeling Course (first 2 lessons free):
Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work! -
#163 How to make your models sample faster, with Adrian Seyboldt & Eliot Carlson
13 augustus 2026 · 1 uur 24 min
Support & Resources
→ Support the show on Patreon
→ Bayesian Modeling Course (first 2 lessons free) Lees meerOur theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work
Takeaways:
Q: What is mass matrix adaptation, in plain terms?
A: Mass matrix adaptation is best understood as an automatic, fairly dumb, but very effective reparameterization of your model. The simplest version, the diagonal mass matrix, just rescales each parameter so its posterior standard deviation becomes one, which is exactly what you'd do by hand if you had the patience. Every time you sample a PyMC or Stan model, this kind of reparameterization is happening under the hood.Q: How does Nutpie's approach to mass matrix adaptation differ from Stan and PyMC's default?
A: Stan and PyMC's default sampler only use one source of information for diagonal mass matrix adaptation: the posterior standard deviation estimated from warm-up draws. Nutpie also uses the gradients of the log density, which HMC is already computing at every step to build its trajectory. For a standard normal distribution, the covariance of the gradients is exactly the inverse covariance of the draws, so Nutpie takes the geometric mean of the two resulting standard deviations. There's no guarantee it's always better, but in practice it usually is.Q: What problem does "Preconditioning Hamiltonian Monte Carlo by Minimizing Fisher Divergence" actually solve?
A: Preconditioning HMC means transforming your target distribution into one that's friendly to sample, but doing that well requires knowing things about the distribution, like its covariance, that sampling itself is supposed to discover. This chicken-and-egg problem is usually handled by sketching a rough estimate from a handful of early warm-up draws, which can burn a large share of total sampling time. Adrian and Eliot's paper formalizes how to make better use of a second signal, the score function, that HMC already computes for f… -
Bayesian Statistics vs. Epistemology
13 augustus 2026 · 5 min
Today's clip is from episode 160, featuring Vaden Masrani. In this conversation, Vaden explores the tension between Bayesian statistics and Bayesian epistemology, and why he sees them as fundamentally different. Lees meer
He explains why Bayesian epistemology can run into problems when trying to explain where hypotheses themselves come from, and argues that an emphasis on finding supporting evidence can encourage confirmation bias rather than genuine scientific inquiry. He also discusses Hempel's paradox, Popper's idea of falsification, and why these philosophical problems don't necessarily undermine Bayesian statistics itself.
Full discussion here
Support & Resources
→ Support the show on Patreon
→ Bayesian Modeling Course (first 2 lessons free):
Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work! -
Bayesian Epistemology Is "Bayes' Theorem Without the Data"
7 augustus 2026 · 4 min
Today's clip is from episode 160, featuring Vaden Masrani. In this conversation, Vaden lays out a sharp critique of Bayesian epistemology - the roughly hundred-year-old philosophical tradition, popular in some Oxford-adjacent circles, that treats subjective probability estimates as legitimate even when there's no data behind them. Lees meer
Vaden's core objection: doing Bayes' theorem on numbers you made up in your head is like fitting a regression line to an empty scatter plot - the math looks rigorous, but there's nothing underneath it. He argues this "math-washing" can trick people into thinking a decision is well-informed simply because it's dressed up in probability language, when frequentists and data-driven Bayesians alike would say the same thing: no data, no model.
Get the full discussion here
Support & Resources
→ Support the show on Patreon
→ Bayesian Modeling Course (first 2 lessons free):
Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work! -
Why Bayesians Have an Edge in AI
3 augustus 2026 · 4 min
Today's clip is from episode 162, featuring Chris Krapu. In this conversation, Chris explains why Bayesian thinking remains surprisingly valuable in today's AI landscape - even when the models themselves aren't explicitly Bayesian. Lees meer
Rather than uncertainty estimation, Chris highlights a different advantage: Bayesian training provides a deep intuition for concepts like priors, sampling, rejection sampling, and high-dimensional geometry, making it much easier to understand and apply modern AI research. He also discusses why Bayesian methods are becoming increasingly relevant for evaluating agentic AI systems, where complex workflows and limited evaluation data make hierarchical models and sensible priors especially powerful.
Get the full discussion here
Support & Resources
→ Support the show on Patreon
→ Bayesian Modeling Course (first 2 lessons free):
Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work! -
#162 Bayesian Hydrology & GPU AI, with Christopher Krapu
28 juli 2026 · 1 uur 5 min
Support & Resources
→ Support the show on Patreon
→ Bayesian Modeling Course (first 2 lessons free) Lees meerOur theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work
Takeaways:
Q: How does putting a Gaussian process on unknown coordinates fix noisy location data in mineral prospecting?
A: In mining and geostatistics, the classic Gaussian process model, known there as kriging, assumes you know exactly where each sample was taken. Chris’ project broke that assumption on purpose: the recorded coordinates for each core sample were only accurate to within a rough radius. By treating the true locations as latent variables and putting a Gaussian process over them jointly with the measurements, the model could still reconstruct the underlying gold-concentration field, even though the exact sampling locations were never known precisely. It's a demonstration that Gaussian processes can absorb structural uncertainty that looks, at first glance, like it should make the problem impossible.
Q: What is "Poverty Bayes," and what did it cost to train a two-million-parameter Bayesian model?
A: Poverty Bayes was Chris’ experiment in seeing how cheaply a large Bayesian model could be trained using modern cloud infrastructure. He fit a hierarchical logistic regression with close to two million parameters, using PyMC's Hamiltonian Monte Carlo on a single A100 GPU rented through Modal, a serverless platform that deploys a Python script straight to GPU hardware with almost no setup. He'd originally guessed it would cost around five dollars, the price of a Big Mac, but the real bill came in an order of magnitude lower. A model that would take a Gibbs sampler weeks to run, and that once required a research lab's dedicated GPU, now costs pocket change and a few minutes of setup.
Q: What's the current bottleneck in Bayesian-at-scale tooling?
A: Chris argues the software has largely caught up: PyMC's JAX backend and NumPyro make GPU-accelera…
-
The Next Step Beyond LLMs: Foundation Models for Inference
22 juli 2026 · 6 min
Today's clip is from episode 161, featuring Luigi Acerbi. In this conversation, Luigi explains one of the biggest engineering bottlenecks facing transformer-based probabilistic models—and how his group found a way around it. Lees meer
The core challenge is that many inference models treat data as an unordered set, making them naturally permutation invariant. That's statistically elegant, but computationally painful: every time a new data point arrives, the model has to recompute attention over the entire dataset from scratch, preventing the kind of KV caching that makes modern language models so efficient.
Luigi walks through his team's solution: a hybrid architecture that keeps the original context fully set-based while introducing a causal-attention buffer for newly arriving data. The result is dramatically faster inference- up to 100× faster in some settings - opening the door to applications like reinforcement learning, active data acquisition, and, ultimately, Luigi's long-term vision of a foundation model for Bayesian inference.
Get the full discussion here
Support & Resources
→ Support the show on Patreon
→ Bayesian Modeling Course (first 2 lessons free)Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work
-
#161 Amortized Inference & Neural Processes, with Luigi Acerbi
16 juli 2026 · 1 uur 32 min
Support & Resources
→ Support the show on Patreon
→ Bayesian Modeling Course (first 2 lessons free) Lees meerOur theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work
Takeaways:
Q: What is Variational Bayesian Monte Carlo (VBMC) and how is it different from Bayesian optimization?
A: VBMC borrows the machinery of Bayesian optimization but aims at a different target. Bayesian optimization fits a Gaussian process surrogate to an expensive function and uses it to hunt for the optimum. VBMC instead treats the log-posterior as the function to model, evaluates it at a few carefully chosen points, and keeps the whole reconstructed shape rather than just its peak. That gives you the full posterior, not a single best-fit value. Where MCMC might need tens of thousands to millions of evaluations, VBMC often reconstructs a good posterior approximation from a few hundred, which matters when each evaluation is slow.Q: When should you reach for PyVBMC, and when is it the wrong tool?
A: Two symptoms tell you PyVBMC might help. First, speed: if a single evaluation of your log density takes on the order of a second, running MCMC over tens of thousands of evaluations becomes painful, and PyVBMC's few-hundred-evaluation budget pays off. Second, dimensionality: because it leans on a Gaussian process surrogate, it works well up to roughly 10 to 15 parameters and degrades beyond that. If your model already runs fine in Stan or PyMC, you do not need it. It shines for expensive, low-dimensional models common in science and engineering, where you are modeling a process rather than composing nice distributions.Full takeaways here
Chapters:
00:18:13 What is Variational Bayesian Monte Carlo (VBMC) and how does it differ from Bayesian optimization?
00:30:21 When should you use VBMC versus BADS in practice?
00:31:20 What is Bayesian Adaptive Direct Search (BADS) and how does its hybrid optimization strategy work?
00:39:18 What are neural processe… -
Bayesian Statistics vs Epistemology, with Vaden Masrani
29 juni 2026 · 1 uur 41 min
Support & Resources
→ Support the show on Patreon
→ Bayesian Modeling Course (first 2 lessons free) Lees meerOur theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work
Takeaways:
Q: What's the difference between Bayesian statistics and Bayesian epistemology?
A: Bayesian statistics uses Bayes' theorem on actual data: you put a prior over parameters, combine it with a likelihood, and the data is allowed to tell you your model is wrong. Vaden loves it. Bayesian epistemology, in his tongue-in-cheek phrase, is "Bayesian statistics minus the statistics" - taking Bayes' theorem as a general account of how anyone should reason under uncertainty, including about events where there is nothing to count. The first is falsifiable and grounded; the second, he argues, lets people attach authoritative-sounding numbers to pure belief.Q: Why is it a problem to put a probability on a one-off future event like human extinction?
A: Because there are no statistics behind it. Vaden's trigger example is Toby Ord's The Precipice, where a data-derived probability (supervolcanoes per millennium) is placed side by side with a probability of extinction-by-superintelligence that came from no data at all. His reaction is the statistician's first instinct: where are the numbers coming from, and what could ever make them come out differently? A subjective degree of belief is fine as a hunch. The trouble starts when it is communicated as though it were an objective, data-grounded frequency.Q: What does Vaden Masrani actually like about Bayesian statistics?
A: The freedom to encode domain knowledge as a prior and have the result respect common sense - estimating an average human height, you can rule out zero and a hundred feet before seeing a single measurement. But the part he keeps stressing is falsifiability: you fit the model, compare it to data, and the data can tell you the model was bad. That contact with reality is exactly what makes the stati… -
Why Bayesian Statistics Is More Computational Than Ever
19 juni 2026 · 5 min
Today's clip is from Episode 158 featuring Stefan Radev. In this conversation, Alex Andorra and Stefan break down a core argument from their paper: Bayesian statistics has never been more computational than it is now, and simulation is the thread that ties the whole workflow together. Lees meer
Stefan parcellates the Bayesian workflow into four stages, and this clip covers the first two. Stage one is model specification, where the workflow community has long recommended prior predictive checks. You can do this informally, just running simulations from your model and eyeballing whether the output meets your expectations, or formally, à la Michael Betancourt, by pushing your model's high-dimensional output through a transformation into a low-dimensional, interpretable space and checking it against reality.
The punchline: a surprising number of models can be discarded before you've even seen real data, yet Stefan notes these checks remain underused in practice.
Stage two is model verification, where the question shifts to whether your inferences are well calibrated. This is the territory of simulation-based calibration and parameter recovery studies, classic tools that have always carried a steep computational price. You simulate thousands of synthetic datasets and run inference on every single one, which is exactly why these checks are so often skipped in papers, even though doing one well can be a contribution in its own right.
Here's where amortized simulation-based inference changes the math entirely. Checks that used to take days now take seconds, and instead of laboriously running inference dataset by dataset, you get millions of posterior samples essentially for free. The calibration checks that the field has always known it should be doing finally become cheap enough to actually do.
Get the full discussion here
Support & Resources
→ Support the show on Patreon
→ Bayesian Modeling Course (first 2 lessons free)Our theme music is « Good Bayesian », by Baba Brinkman…
-
Exact GPs vs Approximations: When to Use Each (and Why It Matters)
10 juni 2026 · 4 min
Today's clip is from episode 159 featuring Matthijs Hollanders. In this conversation, Alex and Matthijs dig into a deceptively practical question: when you're modeling wildlife across space and time with Gaussian Processes, how do you keep the math from becoming computationally unbearable - and what does good engineering actually look like in the field? Lees meer
Matthijs explains that for most real camera trapping datasets, exact GPs still hold up fine. The reason is less about clever math and more about ecological reality: researchers are usually resource-constrained, so datasets tend to be a few hundred sites, not thousands.
And when datasets do get large, they're rarely one giant connected grid - they're clusters of independent regions. That structure is exploitable. Run a separate, smaller GP per region, share the hyperparameters, and you avoid building the massive covariance matrix that makes exact GPs expensive in the first place.
But the more interesting thread is where this is heading. Alex introduces Hilbert Space Gaussian Processes (HSGPs) - an approximation that makes compute time nearly linear in dataset size, rather than cubic. The catch, as Matthijs points out, is that approximations aren't always better: if your dataset isn't large enough to be in the regime where the approximation accuracy kicks in, you're better off with the exact GP and its mathematical guarantees. The rule of thumb is simple - if you can use the vanilla GP, just do it.
Get the full discussion here
Support & Resources
→ Support the show on Patreon
→ Bayesian Modeling Course (first 2 lessons free)Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work
-
#159 Bayesian Occupancy Models, with Matthijs Hollanders
8 juni 2026 · 1 uur 26 min
Support & Resources
→ Support the show on Patreon
→ Bayesian Modeling Course (first 2 lessons free) Lees meerOur theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work
Takeaways:
Q: What is a Bayesian occupancy model and what problem does it solve?
A: An occupancy model accounts for the fact that you don't always detect a species when surveying for it, especially when the species is rare. A naive count of where you found it underestimates true occupancy. The model adds a repeated-measures component: you visit each site multiple times, and from the pattern of detections vs. non-detections it estimates a detection probability. Matthijs framed it as a zero-inflation structure where the zero-inflation happens at the site level rather than the observation level -- which keeps the model conceptually simple, just a standard GLM with a Bernoulli “is the species here at all?” stacked on top of a detection-rate process.Q: What are Automated Recording Units and why don't traditional occupancy models handle them well?
A: ARUs are camera traps and acoustic monitors that record continuously over deployment periods of days, weeks, or months. The data they produce isn't a sequence of discrete human-led surveys; it's a continuous-time observation stream. Traditional occupancy models were designed for the discrete case -- a human visits a site, records yes or no, goes home. With ARUs, the question becomes how to bin or threshold the continuous data without losing the richer signal it actually contains.Q: When should you not reach for occARU?
A: When your dataset is large and your survey interval is fine-grained. The bottleneck is Stan's fitting speed -- years of daily count data across many sites will fit slowly. The workaround is to bin coarser (weekly or monthly), which doesn't hurt occupancy estimation at all and only loses some detection-rate resolution. If you're only interested in occupancy, big grouping windows are fine.
Ful…
-
Can AI Learn What Experts Know? Automating Prior Elicitation with Generative Models
2 juni 2026 · 5 min
Today's clip is from episode 158 featuring Stefan Radev. In this conversation, Alex and Stefan explore a genuinely fascinating problem: how do you turn an expert's intuition into a mathematically valid prior distribution - and can AI help automate that process? Lees meer
Alex explains that prior elicitation is essentially a translation problem. Experts don't walk around thinking in probability distributions - their knowledge lives in intuitions, rules of thumb, and rough ranges. The challenge is converting that into something a Bayesian model can actually use.
The traditional approach? Ask an expert for quantiles or a mean, then parameterize your prior with hyperparameters and simulate until the model-implied quantities match what the expert described. If your pipeline is differentiable end-to-end, you use gradient descent. If not, you fall back to something like Bayesian optimization. Either way, you're iterating toward a prior that genuinely reflects expert knowledge - not just a convenient assumption.
But the really exciting part is what came next. In a follow-up paper, they pushed this further: instead of optimizing within a fixed parametric family (say, a Gaussian), they replaced the prior entirely with a normalizing flow - a flexible generative network - and ran the same procedure. No assumed distribution family. Just let the data and the expert's knowledge shape the prior from scratch.
The catch? More flexibility means more non-identifiability and stability headaches. But the direction is clear: a fully automated, end-to-end pipeline for building priors from non-probabilistic expert knowledge. And in 2026, that pipeline could theoretically be driven by an agent.
Get the full discussion here
Support & Resources
→ Support the show on Patreon
→ Bayesian Modeling Course (first 2 lessons free)Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work
-
#158 Bayesian Workflows & Foundation Models, with Stefan Radev
21 mei 2026 · 1 uur 19 min
Support & Resources
→ Support the show on Patreon
→ Bayesian Modeling Course (first 2 lessons free) Lees meerOur theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work
Takeaways:
Q: Why are prior predictive checks so underused in practice, and how do simulations help?
A: They're underused because researchers don't always think to run them before seeing data -- but also because doing them rigorously (in the style Michael Betancourt advocates, with prior push-forward checks on interpretable summaries) takes effort. Simulations make it cheap to generate thousands of “what-if world” datasets from your model and check whether they look plausible, catching bad priors before you ever touch real data.Q: How can generative AI help with prior elicitation?
A: Rather than forcing a domain expert to choose a distributional family and parameterize it, you can use a generative model to translate their qualitative knowledge directly into a prior. The expert describes what realistic data should look like; the generative model produces synthetic datasets matching that description; those datasets are used to fit a prior distribution. It removes the assumption that experts can think in terms of parameters and replaces it with the more natural question: does this look like your data?Q: What would a foundation model for Bayesian inference actually look like?
A: Stefan's bet is that it won't be a fine-tuned general LLM. The right analogy is chess: you don't fine-tune GPT to play chess, you teach it when to call Stockfish. For Bayesian inference, you'd want a semantic layer – an LLM that understands the analysis goal – calling specialized numerical engines (MCMC samplers, amortized inference networks) that do the actual computation. Agent skills are already a step in this direction; the longer-term vision is engines that have been trained from scratch to generalize across large families of models and priors.Full takeaways here.
Chapters…
-
The Hidden Geometry of Hierarchical Models
13 mei 2026 · 4 min
Today's clip is from Episode 157 featuring Stefan Radev. In this conversation, Alex and Stefan dig into one of the hardest open problems in simulation-based inference — hierarchical models. Lees meer
The core idea: when you move from flat to hierarchical models, you're no longer estimating one set of parameters. You have local parameters that vary by location (or subject, or city) and global parameters that capture what's shared across all of them. And you don't just want each separately — you want the full joint posterior, because that's where the Bayesian magic of shrinkage actually lives.
Stefan builds the problem from the ground up. Start with the simplest hierarchical case: a two-level model. He uses electoral forecasting in France as the example — cities nested inside departments nested inside the whole country.
Now your simulator has to cover all three levels. If that simulator is slow (think: brain emulators, minutes per sample), scaling to hundreds of groups becomes completely intractable. Memory issues, specialized network requirements, the works.
The key insight: this problem has structure you can exploit. The joint posterior factorizes in a particularly nice way — each local parameter depends on its own local data and on the global parameters. That means instead of cramming everything into one giant high-dimensional vector and hoping a neural network figures it out, you can decompose the problem. Estimate local parameters conditioned on local data and the globals. Use composition.
The takeaway: hierarchical models aren't just "harder flat models" - they have a geometry that demands a different architecture. Respecting that structure is what makes amortized inference scale.
Get the full discussion here
Support & Resources
→ Support the show on Patreon
→ Bayesian Modeling Course (first 2 lessons free)Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work
-
#157 Amortized Inference & BayesFlow in Practice, with Stefan Radev
6 mei 2026 · 1 uur 19 min
Support & Resources
→ Support the show on Patreon
→ Bayesian Modeling Course (first 2 lessons free) Lees meerOur theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work
Takeaways:
Q: What is simulation-based inference and what does "sim-to-real" mean?
A: Simulation-based inference (SBI) uses a mechanistic simulator as an epistemic tool: you train a neural network on a large number of labeled simulations and then deploy it on real, unlabeled data. The "sim-to-real" framing captures the key asymmetry -- your network never sees real data during training, only simulations, but it generalizes to real observations at inference time. This is the opposite of the more common "synthetic-for-ML" approach, where fake data is used purely to augment real training data.Q: What is the amortized inference agent skill and what does it do?
A: It's an open-source AI agent skill, co-developed by Stefan and Alexandre, that teaches an AI coding agent to run a complete, state-of-the-art amortized inference workflow. Because amortized inference is recent enough that it's underrepresented in LLM training data, vanilla agents tend to get it wrong. The skill injects the right methodology: it guides the agent to set up the simulator, choose the right network architecture, run a pilot, train with appropriate diagnostics, and produce an actionable report -- without the user needing to know the details.Q: What is calibration coverage and why should you never skip it?
A: Calibration coverage tells you whether your posterior uncertainty is honest -- whether your credible intervals actually contain the true parameter at the right frequency. A model can show poor parameter recovery yet still be well-calibrated (because it's falling back on the prior), or it can appear to recover parameters while being poorly calibrated. Running calibration diagnostics both in-sample and out-of-sample is especially revealing for hierarchical models, which often appear t… -
How to Design Better Experiments with Expected Information Gain
1 mei 2026 · 6 min
Today's clip is from Episode 156 featuring Adam Foster. In this conversation, Adam explains Expected Information Gain (EIG) -the scoring function at the heart of optimal Bayesian experimental design. Lees meer
The core idea: when designing an experiment, you need a way to compare possible designs and pick the best one. EIG is that score - it tells you how much information you expect to gain about your model parameters from a given design. The higher the EIG, the better the design.
Adam builds intuition for EIG from two directions that sound completely different but lead to the same place. First, the Bayesian angle: simulate datasets from your prior predictive distribution, run inference on each, measure how much uncertainty dropped, and average across datasets. Second, a classic puzzle - the 12 prisoners balance scale problem - where the best weighing strategy turns out to be the one that makes all three outcomes (tip left, tip right, balance) equally likely. This maximizes outcome entropy, which is exactly what EIG does: it steers you toward designs where every possible result narrows down your hypotheses as fast as possible.
The takeaway: good experimental design isn't about intuition or convention - it's about making your data work as hard as possible, and EIG gives you a rigorous way to do that.
Get the full discussion here
Support & Resources
→ Support the show on Patreon
→ Bayesian Modeling Course (first 2 lessons free)Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work
-
#156 Bayesian Experimental Design & Active Learning, with Adam Foster
25 april 2026 · 1 uur 17 min
Support & Resources
→ Support the show on Patreon
→ Bayesian Modeling Course (first 2 lessons free) Lees meerOur theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work
Takeaways
Q: What is Bayesian experimental design and what problem does it solve?
A: It's the practice of using a Bayesian model to decide how to collect data before you collect it. Most statistical thinking starts with a fixed dataset. Bayesian experimental design sits upstream -- you have control over experimental parameters (which questions to ask, which reagents to mix, which conditions to test) and you want to choose them optimally. The Bayesian angle is to ask: what new data would most reduce my current uncertainty?Q: When should you actually use Bayesian experimental design?
A: When two conditions hold: you have active control over how data is collected (not just passive observation), and you have a Bayesian model whose prior predictive distribution gives a reasonable picture of what typical data might look like. It's especially valuable when data collection is expensive or irreversible -- when the "committal step" of running an experiment has real cost, it's worth doing the analysis first.Q: What is expected information gain (EIG) and why is it central to Bayesian experimental design?
A: EIG is the score you assign to a candidate experimental design -- the amount of information you expect to gain about your model parameters by running an experiment with that design. You compute it by simulating datasets from your prior predictive, doing Bayesian inference on each, and averaging how much the uncertainty decreased. What's remarkable is that you can derive the same quantity from two completely different starting points -- reducing parameter uncertainty, or maximizing outcome uncertainty while correcting for noise - and arrive at the same formula. That convergence is why EIG keeps being re-discovered independently across fields.Full takeaways he…
-
Pricing Under Uncertainty: A Bayesian Workflow
16 april 2026 · 5 min
Today's clip is from Episode 152 of the podcast, featuring Daniel Saunders. In this conversation, Daniel explores how Bayesian decision theory handles real-world risk aversion beyond the textbook maximum expected utility framework. Lees meer
The key insight: classical Bayesian decision theory assumes risk neutrality, but in practice, people and businesses are risk-averse. Using a pricing optimization example, Daniel shows how uncertainty varies dramatically across price points—lower prices have predictable demand, while higher prices create wide uncertainty in profits. This asymmetry matters when you want safer decisions.
Daniel introduces exponential utility functions—a technique from economics that models diminishing returns on money. By adjusting a risk-aversion parameter, you can see how increasing risk aversion shifts optimal decisions away from high-uncertainty, high-profit scenarios toward more predictable outcomes.
The broader lesson: optimal decision-making requires separating the modeling process from the decision process, allowing you to build in constraints and risk adjustments that pure expected utility maximization would miss.
Get the full discussion here
Support & Resources
→ Support the show on Patreon: https://www.patreon.com/c/learnbayesstats
→ Bayesian Modeling Course (first 2 lessons free): https://topmate.io/alex_andorra/1011122Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work at https://bababrinkman.com/ !
-
#155 Probabilistic Programming for the Real World, with Andreas Munk
8 april 2026 · 1 uur 54 min
Support & Resources
→ Support the show on Patreon
→ Bayesian Modeling Course (first 2 lessons free): Lees meerOur theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work
Takeaways:
Q: Why is bridging deep learning and probabilistic programming so important?
A: Deep learning is extraordinarily good at fitting complex functions, but it throws away uncertainty. Probabilistic programming keeps uncertainty explicit throughout. Combining the two – as in inference compilation – lets you get the expressiveness of neural networks while still doing proper Bayesian inference.Q: What is inference compilation and how does it relate to amortized inference?
A: Amortized inference is the general idea of training a model upfront so you don't have to run expensive inference from scratch every single time. Inference compilation is a specific form of amortized inference where a neural network is trained to propose good posterior samples for a given probabilistic program – essentially learning to do inference rather than computing it fresh each query.Q: What is PyProb and what problems does it solve?
A: PyProb is a probabilistic programming library designed specifically to support amortized inference workflows. It lets you write probabilistic models in Python and then train inference networks on top of them, making methods like inference compilation practical for real-world simulators and scientific models.Full takeaways here.
Chapters:
00:00:00 Introduction to Bayesian Inference and Its Barriers
00:03:51 Andreas Munch's Journey into Statistics
00:10:09 Bridging the Gap: Bayesian Inference in Real-World Applications
00:15:56 Deep Learning Meets Probabilistic Programming
00:22:05 Understanding Inference Compilation and Amortized Inference
00:28:14 Exploring PyProb: A Tool for Amortized Inference
00:33:55 Probabilistic Surrogate Networks and Their Applications
00:38:10 Building Surrogate Models for Probabilistic Programming
00:45:44 Th… -
Bitesize | "What Would Have Happened?" - Bayesian Synthetic Control Explained
2 april 2026 · 5 min
Today's clip is from Episode 154 of the podcast, with Thomas Pinder. Lees meer
In this conversation, Thomas Pinder explains how Bayesian methods naturally lend themselves to causal modeling, and why that matters for real-world business decisions. The key insight is that causal questions in industry are rarely black and white: instead of a single treatment effect, you get a full posterior distribution, credible intervals, and the ability to communicate the probability that an effect is positive, which is far more useful to stakeholders than a p-value.
Thomas then dives into Bayesian Synthetic Control, a reframing of the classic synthetic control method from a constrained optimization problem into a Bayesian regression problem. Rather than optimizing weights on a simplex, you place a Dirichlet prior on the regression coefficients, which turns out to be not just mathematically elegant but practically richer: you can express prior beliefs about how many control units are informative, set the concentration parameter accordingly, or let a gamma hyperprior on that parameter let the data decide. The result is a more flexible, less fragile counterfactual, implemented cleanly in PyMC or NumPyro.
Get the full discussion here
Support & Resources
→ Support the show on Patreon: https://www.patreon.com/c/learnbayesstats
→ Bayesian Modeling Course (first 2 lessons free): https://topmate.io/alex_andorra/1011122Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work at https://bababrinkman.com/ !
-
#154 Bayesian Causal Inference at Scale, with Thomas Pinder
25 maart 2026 · 1 uur 26 min
• Support & get perks! Lees meer
• Bayesian Modeling course (first 2 lessons free)
Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work!
Takeaways:
Q: Why was GPJax created and how does it benefit researchers?
A: GPJax was developed to provide a high-performance, flexible framework for Gaussian processes (GPs) within the JAX ecosystem. It allows researchers to move beyond black-box implementations and easily experiment with custom kernels and model structures while leveraging JAX’s automatic differentiation and GPU acceleration.Q: What are the primary advantages of using Gaussian processes for data modeling?
A: Gaussian processes are highly effective at modeling complex, nonlinear relationships in data. Unlike many machine learning methods that only provide a point estimate, GPs offer built-in uncertainty quantification, which is essential for understanding the reliability of predictions in research and industry.Q: How does the GPJax and NumPyro integration enhance probabilistic modeling?
A: The integration allows users to treat GPJax models as components within a larger NumPyro probabilistic program. This combination enables the use of advanced sampling techniques like NUTS (No-U-Turn Sampler), making it easier to build and fit complex hierarchical models that include Gaussian processes.Q: What are the main challenges when applying Gaussian processes to high-dimensional data?
A: High-dimensional data significantly complicates GP modeling due to the curse of dimensionality and the cubic scaling of computational costs. In high dimensions, defining meaningful distance metrics for kernels becomes harder, often requiring specialized techniques like sparse GPs or dimensionality reduction to remain tractable.Full takeaways here!
Chapters:
11:40 What is GPJax and how does it simplify Gaussian Process modeling?
15:48 How are Bayesian methods used for experimentation and causal inference in industry?
18:40 How do… -
#153 The Neuroscience of Philanthropy, with Cherian Koshy
11 maart 2026 · 1 uur 9 min
• Support & get perks! Lees meer
• Bayesian Modeling course (first 2 lessons free)
Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work !
Takeaways:
Q: Is generosity a natural human trait?
A: Yes, generosity is hardwired in our brains and is essential for social interaction.Q: Why do people say they care about causes but not act on it?
A: There is often a disconnect between stated care for causes and actual action. Understanding the conditions under which generosity aligns with a person's identity is crucial for bridging this gap.Q: How should fundraising efforts be approached?
A: Fundraising should primarily focus on belief updating rather than mere persuasion.Q: What are the benefits of being generous?
A: Generosity has significant mental and physical health benefits, as the brain's reward systems activate when we give, making us feel good.Q: How do our beliefs relate to our actions?
A: Our beliefs about ourselves strongly influence our actions and decisions, including our decision to be generous.Q: Can generosity impact a community?
A: Yes, generosity can be a powerful tool for improving community dynamics.Q: How can technology like AI assist institutions with donors?
A: AI could help institutions remember donors better, improving the donor-institution relationship.Chapters:
00:00 What's the role of Behavioral Science inPhilanthropy
19:57 What is The Neuroscience of Generosity?
24:40 How can we best understand Donor Decision-Making?
32:14 How can we achieve reframe Beliefs and Actions?
35:39 What is the role of Identity in Habit Formation?
38:06 What is the Generosity Gap in Philanthropy?
45:06 How can we reduce Friction in Donation Processes?
48:27 What is the role of AI and Trust in Nonprofits?
52:11 How can we build Predictive Models for Donor Behavior?
55:41 What is the role of Empathy in Sales and Stakeholder Engagement?
01:00:46 How can we best align ideas with Stakeholder Beliefs?
01:02:06… -
Bitesize | How To Model Risk Aversion In Pricing?
4 maart 2026 · 4 min
Today's clip is from Episode 152 of the podcast, with Daniel Saunders. Lees meer
In this conversation, Daniel Saunders explains how to incorporate risk aversion into Bayesian price optimization. The key insight is that uncertainty around expected profit is asymmetric across price points, low prices yield more predictable (if modest) returns, while high prices introduce much wider uncertainty. Rather than simply maximizing expected profit, you can pass profit through an exponential utility function that models diminishing returns, a well-established idea from economics.
This adds an adjustable risk aversion parameter to the optimization: as risk aversion increases, the model shifts toward more conservative price recommendations, trading off potentially large but uncertain gains for outcomes with tighter, more reliable distributions.
Get the full discussion here
• Join this channel to get access to perks:
https://www.patreon.com/c/learnbayesstats• Intro to Bayes Course (first 2 lessons free): https://topmate.io/alex_andorra/503302
• Advanced Regression Course (first 2 lessons free): https://topmate.io/alex_andorra/1011122Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work at https://bababrinkman.com/ !
-
#152 A Bayesian decision theory workflow, with Daniel Saunders
26 februari 2026 · 1 uur 19 min
• Support & get perks! Lees meer
• Proudly sponsored by PyMC Labs!
• Intro to Bayes and Advanced Regression courses (first 2 lessons free)
Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work !
Chapters:
00:00 The Importance of Decision-Making in Data Science
06:41 From Philosophy to Bayesian Statistics
14:57 The Role of Soft Skills in Data Science
18:19 Understanding Decision Theory Workflows
22:43 Shifting Focus from Accuracy to Business Value
26:23 Leveraging PyTensor for Optimization
34:27 Applying Optimal Decision-Making in Industry
40:06 Understanding Utility Functions in Regulation
41:35 Introduction to Obeisance Decision Theory Workflow
42:33 Exploring Price Elasticity and Demand
45:54 Optimizing Profit through Bayesian Models
51:12 Risk Aversion and Utility Functions
57:18 Advanced Risk Management Techniques
01:01:08 Practical Applications of Bayesian Decision-Making
01:06:54 Future Directions in Bayesian Inference
01:10:16 The Quest for Better Inference Algorithms
01:15:01 Dinner with a Polymath: Herbert Simon
Thank you to my Patrons for making this episode possible!
Links from the show:
Come meet Alex at the Field of Play Conference in Manchester, UK, March 27, 2026! https://www.fieldofplay.co.uk/
A Bayesian decision theory workflow
Daniel's website, LinkedIn and GitHub
LBS #124 State Space Models & Structural Time Series, with Jesse Grabowski
LBS #123 BART & The Future of Bayesian Tools, with Osvaldo Martin
LBS #74 Optimizing NUTS and Developing the ZeroSumNormal Distribution, with Adrian Seyboldt
LBS #76 The Past, Present & Future of Stan, with Bob Carpenter
-
BITESIZE | How Do Diffusion Models Work?
19 februari 2026 · 4 min
Today's clip is from Episode 151 of the podcast, with Jonas Arruda Lees meer
In this conversation, Jonas Arruda explains how diffusion models generate data by learning to reverse a noise process. The idea is to start from a simple distribution like Gaussian noise and gradually remove noise until the target distribution emerges. This is done through a forward process that adds noise to clean parameters and a backward process that learns how to undo that corruption. A noise schedule controls how much noise is added or removed at each step, guiding the transformation from pure randomness back to meaningful structure.
Get the full discussion here
• Join this channel to get access to perks:
https://www.patreon.com/c/learnbayesstats• Intro to Bayes Course (first 2 lessons free): https://topmate.io/alex_andorra/503302
• Advanced Regression Course (first 2 lessons free): https://topmate.io/alex_andorra/1011122Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work at https://bababrinkman.com/ !
-
#151 Diffusion Models in Python, a Live Demo with Jonas Arruda
12 februari 2026 · 1 uur 36 min
• Support & get perks! Lees meer
• Proudly sponsored by PyMC Labs!
• Intro to Bayes and Advanced Regression courses (first 2 lessons free)
Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work !
Chapters:
00:00 Exploring Generative AI and Scientific Modeling
10:27 Understanding Simulation-Based Inference (SBI) and Its Applications
15:59 Diffusion Models in Simulation-Based Inference
19:22 Live Coding Session: Implementing Baseflow for SBI
34:39 Analyzing Results and Diagnostics in Simulation-Based Inference
46:18 Hierarchical Models and Amortized Bayesian Inference
48:14 Understanding Simulation-Based Inference (SBI) and Its Importance
49:14 Diving into Diffusion Models: Basics and Mechanisms
50:38 Forward and Backward Processes in Diffusion Models
53:03 Learning the Score: Training Diffusion Models
54:57 Inference with Diffusion Models: The Reverse Process
57:36 Exploring Variants: Flow Matching and Consistency Models
01:01:43 Benchmarking Different Models for Simulation-Based Inference
01:06:41 Hierarchical Models and Their Applications in Inference
01:14:25 Intervening in the Inference Process: Adding Constraints
01:25:35 Summary of Key Concepts and Future DirectionsThank you to my Patrons for making this episode possible!
Links from the show:
- Come meet Alex at the Field of Play Conference in Manchester, UK, March 27, 2026!
- Jonas's Diffusion for SBI Tutorial & Review (Paper & Code)
- The BayesFlow Library
- Jonas on LinkedIn
- Jonas on GitHub
- Further reading for more mathematical details: Holderrieth & Erives
- 150 Fast Bayesian Deep Learning, with David Rügamer, Emanuel Sommer & Jakob Robnik
- 107 Amortized Bayesian Inference with Deep Neural Networks, with Marvin Schmitt -
#150 Fast Bayesian Deep Learning, with David Rügamer, Emanuel Sommer & Jakob Robnik
28 januari 2026 · 1 uur 20 min
• Support & get perks! Lees meer
• Proudly sponsored by PyMC Labs!
• Intro to Bayes and Advanced Regression courses (first 2 lessons free)
Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work !
Chapters:
00:00 Scaling Bayesian Neural Networks
04:26 Origin Stories of the Researchers
09:46 Research Themes in Bayesian Neural Networks
12:05 Making Bayesian Neural Networks Fast
16:19 Microcanonical Langevin Sampler Explained
22:57 Bottlenecks in Scaling Bayesian Neural Networks
29:09 Practical Tools for Bayesian Neural Networks
36:48 Trade-offs in Computational Efficiency and Posterior Fidelity
40:13 Exploring High Dimensional Gaussians
43:03 Practical Applications of Bayesian Deep Ensembles
45:20 Comparing Bayesian Neural Networks with Standard Approaches
50:03 Identifying Real-World Applications for Bayesian Methods
57:44 Future of Bayesian Deep Learning at Scale
01:05:56 The Evolution of Bayesian Inference Packages
01:10:39 Vision for the Future of Bayesian StatisticsThank you to my Patrons for making this episode possible!
Come meet Alex at the Field of Play Conference in Manchester, UK, March 27, 2026!
Links from the show:
David Rügamer:
* Website
* Google Scholar
* GitHubEmanuel Sommer:
* Website
* GitHub
* Google ScholarJakob Robnik:
* Google Scholar
* GitHub
* Microcanonical Langevin paper
* LinkedIn -
BITESIZE | Building Resilience in Modern Tech Careers
21 januari 2026 · 25 min
Today’s clip is from episode 149 of the podcast, with Alana Karen. Lees meer
This conversation explores the evolving landscape of technology, particularly in Silicon Valley, focusing on the cultural shifts due to mass layoffs, the debate over remote work, and the impact of AI on job roles and priorities. The discussion highlights the importance of adapting to these changes and preparing for the future by developing complex skills that AI cannot easily replicate.
Get the full discussion here!
• Join this channel to get access to perks:
https://www.patreon.com/c/learnbayesstats• Intro to Bayes Course (first 2 lessons free): https://topmate.io/alex_andorra/503302
• Advanced Regression Course (first 2 lessons free): https://topmate.io/alex_andorra/1011122Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work at https://bababrinkman.com/ !
-
#149 The Future of Work in Tech, with Alana Karen
14 januari 2026 · 1 uur 33 min
• Support & get perks! Lees meer
• Proudly sponsored by PyMC Labs!
• Intro to Bayes and Advanced Regression courses (first 2 lessons free)
Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work !
Chapters:
11:37 The Hard Tech Era
21:08 The Shift in Tech Work Culture
28:49 AI's Impact on Job Security and Work Dynamics
34:33 Adapting to AI: Skills for the Future
45:56 Understanding AI Models and Their Limitations
47:25 The Importance of Diversity in AI Development
54:34 Positioning Technical Talent for Job Security
57:58 Building Resilience in Uncertain Times
01:06:33 Recognizing Diverse Ambitions in Career Progression
01:12:51 The Role of Managers in Employee Retention
01:26:55 Solving Complex Problems with AI and InnovationThank you to my Patrons for making this episode possible!
Links from the show:
Alana's latest book (Use code BAYESIAN for 10% off + a free interview preparation download PDF)
Alana’s Substack
Alana on Linkedin
Alana on Instagram
The Obstacle Is the Way – The Timeless Art of Turning Trials into Triumph
Courage Is Calling – Fortune Favours the Brave
-
BITESIZE | The Trial Design That Learns in Real Time
7 januari 2026 · 22 min
Today’s clip is from episode 148 of the podcast, with Scott Berry. Lees meer
In this conversation, Alex and Scott discuss emphasizing the shift from frequentist to Bayesian approaches in clinical trials.
They highlight the limitations of traditional trial designs and the advantages of adaptive and platform trials, particularly in the context of COVID-19 treatment.
The discussion provides insights into the complexities of trial design and the innovative methodologies that are shaping the future of medical research.
Get the full discussion here!
• Join this channel to get access to perks: https://www.patreon.com/c/learnbayesstats
• Intro to Bayes Course (first 2 lessons free): https://topmate.io/alex_andorra/503302
• Advanced Regression Course (first 2 lessons free): https://topmate.io/alex_andorra/1011122
Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work at https://bababrinkman.com/ !
-
#148 Adaptive Trials, Bayesian Thinking, and Learning from Data, with Scott Berry
30 december 2025 · 1 uur 25 min
• Support & get perks! Lees meer
• Proudly sponsored by PyMC Labs. Get in touch and tell them you come from LBS!
• Intro to Bayes and Advanced Regression courses (first 2 lessons free)
Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work !
Chapters:
13:16 Understanding Adaptive and Platform Trials
25:25 Real-World Applications and Innovations in Trials
34:11 Challenges in Implementing Bayesian Adaptive Trials
42:09 The Birth of a Simulation Tool
44:10 The Importance of Simulated Data
48:36 Lessons from High-Stakes Trials
52:53 Navigating Adaptive Trial Designs
56:55 Communicating Complexity to Stakeholders
01:02:29 The Future of Clinical Trials
01:10:24 Skills for the Next Generation of Statisticians
Thank you to my Patrons for making this episode possible!
Yusuke Saito, Avi Bryant, Giuliano Cruz, Tradd Salvo, William Benton, James Ahloy, Robin Taylor,, Chad Scherrer, Zwelithini Tunyiswa, Bertrand Wilden, James Thompson, Stephen Oates, Gian Luca Di Tanna, Jack Wells, Matthew Maldonado, Ian Costley, Ally Salim, Larry Gill, Ian Moran, Paul Oreto, Colin Caprani, Colin Carroll, Nathaniel Burbank, Michael Osthege, Rémi Louf, Clive Edelsten, Henri Wallen, Hugo Botha, Vinh Nguyen, Marcin Elantkowski, Adam C. Smith, Will Kurt, Andrew Moskowitz, Hector Munoz, Marco Gorelli, Simon Kessell, Bradley Rode, Patrick Kelley, Rick Anderson, Casper de Bruin, Michael Hankin, Cameron Smith, Tomáš Frýda, Ryan Wesslen, Andreas Netti, Riley King, Yoshiyuki Hamajima, Sven De Maeyer, Michael DeCrescenzo, Fergal M, Mason Yahr, Naoya Kanai, Aubrey Clayton, Omri Har Shemesh, Scott Anthony Robson, Robert Yolken, Or Duek, Pavel Dusek, Paul Cox, Andreas Kröpelin, Raphaël R, Nicolas Rode, Gabriel Stechschulte, Arkady, Kurt TeKolste, Marcus Nölke, Maggi Mackintosh, Grant Pezzolesi, Joshua Meehl, Javier Sabio, Kristian Higgins, Matt Rosinski, Luis Fonseca, Dante Gates, Matt Niccolls, Maksim Kuznecov, Michael Thomas, Luke Gorrie, Cory K…
-
BITESIZE | Making Variational Inference Reliable: From ADVI to DADVI
17 december 2025 · 22 min
Today’s clip is from episode 147 of the podcast, with Martin Ingram. Lees meer
Alex and Martin discuss the intricacies of variational inference, particularly focusing on the ADVI method and its challenges. They explore the evolution of approximate inference methods, the significance of mean field variational inference, and the innovative linear response technique for covariance estimation.
The discussion also delves into the trade-offs between stochastic and deterministic optimization techniques, providing insights into their implications for Bayesian statistics.
Get the full discussion here.
Intro to Bayes Course (first 2 lessons free)
Advanced Regression Course (first 2 lessons free)
Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work!
Visit our Patreon page to unlock exclusive Bayesian swag ;)
Transcript
This is an automatic transcript and may therefore contain errors. Please get in touch if you're willing to correct them.
-
#147 Fast Approximate Inference without Convergence Worries, with Martin Ingram
12 december 2025 · 1 uur 10 min
Proudly sponsored by PyMC Labs, the Bayesian Consultancy. Book a call, or get in touch! Lees meer
Intro to Bayes Course (first 2 lessons free)
Advanced Regression Course (first 2 lessons free)
Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work!
Visit our Patreon page to unlock exclusive Bayesian swag ;)
Takeaways:
DADVI is a new approach to variational inference that aims to improve speed and accuracy.
DADVI allows for faster Bayesian inference without sacrificing model flexibility.
Linear response can help recover covariance estimates from mean estimates.
DADVI performs well in mixed models and hierarchical structures.
Normalizing flows present an interesting avenue for enhancing variational inference.
DADVI can handle large datasets effectively, improving predictive performance.
Future enhancements for DADVI may include GPU support and linear response integration.
Chapters:
13:17 Understanding DADVI: A New Approach
21:54 Mean Field Variational Inference Explained
26:38 Linear Response and Covariance Estimation
31:21 Deterministic vs Stochastic Optimization in DADVI
35:00 Understanding DADVI and Its Optimization Landscape
37:59 Theoretical Insights and Practical Applications of DADVI
42:12 Comparative Performance of DADVI in Real Applications
45:03 Challenges and Effectiveness of DADVI in Various Models
48:51 Exploring Future Directions for Variational Inference
53:04 Final Thoughts and Advice for Practitioners
Thank you to my Patrons for making this episode possible!
Yusuke Saito, Avi Bryant, Giuliano Cruz, James Wade, Tradd Salvo, William Benton, James Ahloy, Robin Taylor, Chad Scherrer, Zwelithini Tunyiswa, Bertrand Wilden, James Thompson, Stephen Oates, Gian Luca Di Tanna, Jack Wells, Matthew Maldonado, Ian Costley, Ally Salim, Larry Gill, Ian Moran, Paul Oreto, Colin Caprani, Colin Carroll, Nathaniel Burbank, Michael Osthege, Rémi Louf, Clive Edelsten, Henri Wallen, Hugo Botha, Vinh Ng…
-
BITESIZE | Why Bayesian Stats Matter When the Physics Gets Extreme
5 december 2025 · 19 min
Today’s clip is from episode 146 of the podcast, with Ethan Smith. Lees meer
Alex and Ethan discuss the application of Bayesian inference in high energy density physics, particularly in analyzing complex data sets. They highlight the advantages of Bayesian techniques, such as incorporating prior knowledge and managing uncertainties.
They also shares insights from an ongoing experimental project focused on measuring the equation of state of plasma at extreme pressures. Finally, Alex and Ethan advocate for best practices in managing large codebases and ensuring model reliability.
Get the full discussion here.
Intro to Bayes Course (first 2 lessons free)
Advanced Regression Course (first 2 lessons free)
Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work!
Visit our Patreon page to unlock exclusive Bayesian swag ;)
Transcript
This is an automatic transcript and may therefore contain errors. Please get in touch if you're willing to correct them.
-
#146 Lasers, Planets, and Bayesian Inference, with Ethan Smith
27 november 2025 · 1 uur 35 min
Proudly sponsored by PyMC Labs, the Bayesian Consultancy. Book a call, or get in touch! Lees meer
Intro to Bayes Course (first 2 lessons free)
Advanced Regression Course (first 2 lessons free)
Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work!
Visit our Patreon page to unlock exclusive Bayesian swag ;)
Takeaways:
Ethan's research involves using lasers to compress matter to extreme conditions to study astrophysical phenomena.
Bayesian inference is a key tool in analyzing complex data from high energy density experiments.
The future of high energy density physics lies in developing new diagnostic technologies and increasing experimental scale.
High energy density physics can provide insights into planetary science and astrophysics.
Emerging technologies in diagnostics are set to revolutionize the field.
Ethan's dream project involves exploring picno nuclear fusion.
Chapters:
14:31 Understanding High Energy Density Physics and Plasma Spectroscopy
21:24 Challenges in Data Analysis and Experimentation
36:11 The Role of Bayesian Inference in High Energy Density Physics
47:17 Transitioning to Advanced Sampling Techniques
51:35 Best Practices in Model Development
55:30 Evaluating Model Performance
01:02:10 The Role of High Energy Density Physics
01:11:15 Innovations in Diagnostic Technologies
01:22:51 Future Directions in Experimental Physics
01:26:08 Advice for Aspiring Scientists
Thank you to my Patrons for making this episode possible!
Yusuke Saito, Avi Bryant, Giuliano Cruz, James Wade, Tradd Salvo, William Benton, James Ahloy, Robin Taylor, Chad Scherrer, Zwelithini Tunyiswa, Bertrand Wilden, James Thompson, Stephen Oates, Gian Luca Di Tanna, Jack Wells, Matthew Maldonado, Ian Costley, Ally Salim, Larry Gill, Ian Moran, Paul Oreto, Colin Caprani, Colin Carroll, Nathaniel Burbank, Michael Osthege, Rémi Louf, Clive Edelsten, Henri Wallen, Hugo Botha, Vinh Nguyen, Marcin Elantkowski, Adam C. Smith…
-
BITESIZE | How to Thrive in an AI-Driven Workplace?
20 november 2025 · 20 min
Today’s clip is from episode 145 of the podcast, with Jordan Thibodeau. Lees meer
Alexandre Andorra and Jordan Thibodeau discuss the transformative impact of AI on productivity, career opportunities in the tech industry, and the intricacies of the job interview process.
They emphasize the importance of expertise, networking, and the evolving landscape of tech companies, while also providing actionable advice for individuals looking to enhance their careers in AI and related fields.
Get the full discussion here.
Intro to Bayes Course (first 2 lessons free)
Advanced Regression Course (first 2 lessons free)
Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work!
Visit our Patreon page to unlock exclusive Bayesian swag ;)
Transcript
This is an automatic transcript and may therefore contain errors. Please get in touch if you're willing to correct them.
-
#145 Career Advice in the Age of AI, with Jordan Thibodeau
12 november 2025 · 1 uur 52 min
Proudly sponsored by PyMC Labs, the Bayesian Consultancy. Book a call, or get in touch! Lees meer
Intro to Bayes Course (first 2 lessons free)
Advanced Regression Course (first 2 lessons free)
Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work!
Visit our Patreon page to unlock exclusive Bayesian swag ;)
Thank you to my Patrons for making this episode possible!
Yusuke Saito, Avi Bryant, Giuliano Cruz, James Wade, Tradd Salvo, William Benton, James Ahloy, Robin Taylor, Chad Scherrer, Zwelithini Tunyiswa, Bertrand Wilden, James Thompson, Stephen Oates, Gian Luca Di Tanna, Jack Wells, Matthew Maldonado, Ian Costley, Ally Salim, Larry Gill, Ian Moran, Paul Oreto, Colin Caprani, Colin Carroll, Nathaniel Burbank, Michael Osthege, Rémi Louf, Clive Edelsten, Henri Wallen, Hugo Botha, Vinh Nguyen, Marcin Elantkowski, Adam C. Smith, Will Kurt, Andrew Moskowitz, Hector Munoz, Marco Gorelli, Simon Kessell, Bradley Rode, Patrick Kelley, Rick Anderson, Casper de Bruin, Michael Hankin, Cameron Smith, Tomáš Frýda, Ryan Wesslen, Andreas Netti, Riley King, Yoshiyuki Hamajima, Sven De Maeyer, Michael DeCrescenzo, Fergal M, Mason Yahr, Naoya Kanai, Aubrey Clayton, Omri Har Shemesh, Scott Anthony Robson, Robert Yolken, Or Duek, Pavel Dusek, Paul Cox, Andreas Kröpelin, Raphaël R, Nicolas Rode, Gabriel Stechschulte, Arkady, Kurt TeKolste, Marcus Nölke, Maggi Mackintosh, Grant Pezzolesi, Joshua Meehl, Javier Sabio, Kristian Higgins, Matt Rosinski, Luis Fonseca, Dante Gates, Matt Niccolls, Maksim Kuznecov, Michael Thomas, Luke Gorrie, Cory Kiser, Julio, Edvin Saveljev, Frederick Ayala, Jeffrey Powell, Gal Kampel, Adan Romero, Will Geary, Blake Walters, Jonathan Morgan, Francesco Madrisotti, Ivy Huang, Gary Clarke, Robert Flannery, Rasmus Hindström, Stefan, Corey Abshire, Mike Loncaric, David McCormick, Ronald Legere, Sergio Dolia, Michael Cao, Yiğit Aşık, Suyog Chandramouli and Guillaume Berthon.
Takeaways:
AI is reshaping the workpl…
-
BITESIZE | Why is Bayesian Deep Learning so Powerful?
5 november 2025 · 19 min
Today’s clip is from episode 144 of the podcast, with Maurizio Filippone. Lees meer
In this conversation, Alex and Maurizio delve into the intricacies of Gaussian processes and their deep learning counterparts. They explain the foundational concepts of Gaussian processes, the transition to deep Gaussian processes, and the advantages they offer in modeling complex data.
The discussion also touches on practical applications, model selection, and the evolving landscape of machine learning, particularly in relation to transfer learning and the integration of deep learning techniques with Gaussian processes.
Get the full discussion here.
Intro to Bayes Course (first 2 lessons free)
Advanced Regression Course (first 2 lessons free)
Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work!
Visit our Patreon page to unlock exclusive Bayesian swag ;)
Transcript
This is an automatic transcript and may therefore contain errors. Please get in touch if you're willing to correct them.
-
#144 Why is Bayesian Deep Learning so Powerful, with Maurizio Filippone
30 oktober 2025 · 1 uur 28 min
Sign up for Alex's first live cohort, about Hierarchical Model building! Lees meer
Get 25% off "Building AI Applications for Data Scientists and Software Engineers"
Proudly sponsored by PyMC Labs, the Bayesian Consultancy. Book a call, or get in touch!
Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work!
Visit our Patreon page to unlock exclusive Bayesian swag ;)
Takeaways:
Why GPs still matter: Gaussian Processes remain a go-to for function estimation, active learning, and experimental design – especially when calibrated uncertainty is non-negotiable.
Scaling GP inference: Variational methods with inducing points (as in GPflow) make GPs practical on larger datasets without throwing away principled Bayes.
MCMC in practice: Clever parameterizations and gradient-based samplers tighten mixing and efficiency; use MCMC when you need gold-standard posteriors.
Bayesian deep learning, pragmatically: Stochastic-gradient training and approximate posteriors bring Bayesian ideas to neural networks at scale.
Uncertainty that ships: Monte Carlo dropout and related tricks provide fast, usable uncertainty – even if they’re approximations.
Model complexity ≠ model quality: Understanding capacity, priors, and inductive bias is key to getting trustworthy predictions.
Deep Gaussian Processes: Layered GPs offer flexibility for complex functions, with clear trade-offs in interpretability and compute.
Generative models through a Bayesian lens: GANs and friends benefit from explicit priors and uncertainty – useful for safety and downstream decisions.
Tooling that matters: Frameworks like GPflow lower the friction from idea to implementation, encouraging reproducible, well-tested modeling.
Where we’re headed: The future of ML is uncertainty-aware by default – integrating UQ tightly into optimization, design, and deployment.
Chapters:
08:44 Function Estimation and Bayesian Deep Learning
10:41 Understanding Deep Gaussian Proc…