Proudly sponsored by PyMC Labs, the Bayesian Consultancy. Book a call, or get in touch!

• 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:

• Teemu focuses on calibration assessments and predictive checking in Bayesian workflows.
• Simulation-based calibration (SBC) checks model implementation
• SBC involves drawing realizations from prior and generating prior predictive data.
• Visual predictive checking is crucial for assessing model predictions.
• Prior predictive checks should be done before looking at data.
• Posterior SBC focuses on the area of parameter space most relevant to the data.
• Challenges in SBC include inference time.
• Visualizations complement numerical metrics in Bayesian modeling.
• Amortized Bayesian inference benefits from SBC for quick posterior checks. The calibration of Bayesian models is more intuitive than Frequentist models.
• Choosing the right visualization depends on data characteristics.
• Using multiple visualization methods can reveal different insights.
• Visualizations should be viewed as models of the data.
• Goodness of fit tests can enhance visualization accuracy.
• Uncertainty visualization is crucial but often overlooked.

Chapters:

09:53 Understanding Simulation-Based Calibration (SBC)

15:03 Practical Applications of SBC in Bayesian Modeling

22:19 Challenges in Developing Posterior SBC

29:41 The Role of SBC in Amortized Bayesian Inference

33:47 The Importance of Visual Predictive Checking

36:50 Predictive Checking and Model Fitting

38:08 The Importance of Visual Checks

40:54 Choosing Visualization Types

49:06 Visualizations as Models

55:02 Uncertainty Visualization in Bayesian Modeling

01:00:05 Future Trends in Probabilistic Modeling

Thank you to my Patrons for making this episode possible!

Yusuke Saito, Avi Bryant, Ero Carrera, Giuliano Cruz, Tim Gasser, James Wade, Tradd Salvo, William Benton, James Ahloy, Robin Taylor,, Chad Scherrer, Zwelithini Tunyiswa, Bertrand...

ICYMI, I'll be in London next week, for a live episode of the Learning Bayesian Statistics podcast 🍾

Come say hi on June 24 at Imperial College London! We'll be talking about uncertainty quantification — not just in theory, but in the messy, practical reality of building models that are supposed to work in the real world.

🎟️ Get your tickets!

Some of the questions we’ll unpack:

🔍 Why is it so hard to model uncertainty reliably?

⚠️ How do overconfident models break things in production?

🧠 What tools and frameworks help today?

🔄 What do we need to rethink if we want robust ML over the next decade?

Joining me on stage: the brilliant Mélodie Monod, Yingzhen Li and François-Xavier Briol -- researchers doing cutting-edge work on these questions, across Bayesian methods, statistical learning, and real-world ML deployment.

A huge thank you to Oliver Ratmann for setting this up!

📍 Imperial-X, White City Campus (Room LRT 608)

🗓️ June 24, 11:30–13:00

🎙️ Doors open at 11:30 — we start at noon sharp

Come say hi, ask hard questions, and be part of the recording.

🎟️ Get your tickets!

• 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, Ero Carrera, Giuliano Cruz, Tim Gasser, 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, Philippe Labonde, 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, Steven Rowland, Aubrey Clayton, Jeannine Sue, 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, Gergely Juhasz, Marcus Nölke, Maggi Mackintosh,...

Today’s clip is from episode 134 of the podcast, with David Kohns.

Alex and David discuss the future of probabilistic programming, focusing on advancements in time series modeling, model selection, and the integration of AI in prior elicitation.

The discussion highlights the importance of setting appropriate priors, the challenges of computational workflows, and the potential of normalizing flows to enhance Bayesian inference.

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.

Proudly sponsored by PyMC Labs, the Bayesian Consultancy. Book a call, or get in touch!

• 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:

• Setting appropriate priors is crucial to avoid overfitting in models.
• R-squared can be used effectively in Bayesian frameworks for model evaluation.
• Dynamic regression can incorporate time-varying coefficients to capture changing relationships.
• Predictively consistent priors enhance model interpretability and performance.
• Identifiability is a challenge in time series models.
• State space models provide structure compared to Gaussian processes.
• Priors influence the model's ability to explain variance.
• Starting with simple models can reveal interesting dynamics.
• Understanding the relationship between states and variance is key.
• State-space models allow for dynamic analysis of time series data.
• AI can enhance the process of prior elicitation in statistical models.

Chapters:

10:09 Understanding State Space Models

14:53 Predictively Consistent Priors

20:02 Dynamic Regression and AR Models

25:08 Inflation Forecasting

50:49 Understanding Time Series Data and Economic Analysis

57:04 Exploring Dynamic Regression Models

01:05:52 The Role of Priors

01:15:36 Future Trends in Probabilistic Programming

01:20:05 Innovations in Bayesian Model Selection

Thank you to my Patrons for making this episode possible!

Yusuke Saito, Avi Bryant, Ero Carrera, Giuliano Cruz, Tim Gasser, 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, Philippe Labonde, Michael Hankin, Cameron Smith, Tomáš Frýda, Ryan Wesslen, Andreas Netti, Riley King, Yoshiyuki...

Today’s clip is from episode 133 of the podcast, with Sean Pinkney & Adrian Seyboldt.

The conversation delves into the concept of Zero-Sum Normal and its application in statistical modeling, particularly in hierarchical models.

Alex, Sean and Adrian discuss the implications of using zero-sum constraints, the challenges of incorporating new data points, and the importance of distinguishing between sample and population effects.

They also explore practical solutions for making predictions based on population parameters and the potential for developing tools to facilitate these 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.

Proudly sponsored by PyMC Labs, the Bayesian Consultancy. Book a call, or get in touch!

• 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:

• Zero Sum constraints allow for better sampling and estimation in hierarchical models.
• Understanding the difference between population and sample means is crucial.
• A library for zero-sum normal effects would be beneficial.
• Practical solutions can yield decent predictions even with limitations.
• Cholesky parameterization can be adapted for positive correlation matrices.
• Understanding the geometry of sampling spaces is crucial.
• The relationship between eigenvalues and sampling is complex.
• Collaboration and sharing knowledge enhance research outcomes.
• Innovative approaches can simplify complex statistical problems.

Chapters:

03:35 Sean Pinkney's Journey to Bayesian Modeling

11:21 The Zero-Sum Normal Project Explained

18:52 Technical Insights on Zero-Sum Constraints

32:04 Handling New Elements in Bayesian Models

36:19 Understanding Population Parameters and Predictions

49:11 Exploring Flexible Cholesky Parameterization

01:07:23 Closing Thoughts and Future Directions

Thank you to my Patrons for making this episode possible!

Yusuke Saito, Avi Bryant, Ero Carrera, Giuliano Cruz, Tim Gasser, 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, Philippe Labonde, 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, Steven Rowland, Aubrey Clayton, Jeannine Sue, 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, Gergely Juhasz, Marcus Nölke, Maggi Mackintosh, Grant Pezzolesi, Avram Aelony, Joshua Meehl, Javier Sabio, Kristian Higgins, Alex Jones, Gregorio Aguilar, Matt Rosinski, Bart Trudeau, 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...

Today’s clip is from episode 132 of the podcast, with Tom Griffiths.

Tom and Alex Andorra discuss the fundamental differences between human intelligence and artificial intelligence, emphasizing the constraints that shape human cognition, such as limited data, computational resources, and communication bandwidth.

They explore how AI systems currently learn and the potential for aligning AI with human cognitive processes.

The discussion also delves into the implications of AI in enhancing human decision-making and the importance of understanding human biases to create more effective AI systems.

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.

Proudly sponsored by PyMC Labs, the Bayesian Consultancy. Book a call, or get in touch!

• 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:

• Computational cognitive science seeks to understand intelligence mathematically.
• Bayesian statistics is crucial for understanding human cognition.
• Inductive biases help explain how humans learn from limited data.
• Eliciting prior distributions can reveal implicit beliefs.
• The wisdom of individuals can provide richer insights than averaging group responses.
• Generative AI can mimic human cognitive processes.
• Human intelligence is shaped by constraints of data, computation, and communication.
• AI systems operate under different constraints than human cognition. Human intelligence differs fundamentally from machine intelligence.
• Generative AI can complement and enhance human learning.
• AI systems currently lack intrinsic human compatibility.
• Language training in AI helps align its understanding with human perspectives.
• Reinforcement learning from human feedback can lead to misalignment of AI goals.
• Representational alignment can improve AI's understanding of human concepts.
• AI can help humans make better decisions by providing relevant information.
• Research should focus on solving problems rather than just methods.

Chapters:

00:00 Understanding Computational Cognitive Science

13:52 Bayesian Models and Human Cognition

29:50 Eliciting Implicit Prior Distributions

38:07 The Relationship Between Human and AI Intelligence

45:15 Aligning Human and Machine Preferences

50:26 Innovations in AI and Human Interaction

55:35 Resource Rationality in Decision Making

01:00:07 Language Learning in AI Models

01:06:04 Inductive Biases in Language Learning

01:11:55 Advice for Aspiring Cognitive Scientists

01:21:19 Future Trends in Cognitive Science and AI

Thank you to my Patrons for making this episode possible!

Yusuke Saito, Avi Bryant, Ero Carrera, Giuliano Cruz,...