iiinova — where your digital self keeps evolving

Reposted by Charles Margossian

Aki Vehtari @avehtari.bsky.social · 08/09/2026

I'm looking for doctoral students, postdocs and research fellows to work with on Bayesian Workflow. Flexible starting time

02115

Reposted by Charles Margossian

Richard McElreath 🐈‍⬛ @rmcelreath.bsky.social · 25/08/2026

Someone emailed me to ask if my lectures are online anywhere, so yes here is the link to most recent lectures. These lectures are free and free of Cyclospora

2479

Reposted by Charles Margossian

Aki Vehtari @avehtari.bsky.social · 21/08/2026

Given all the discussions about Laplace and Jacobians at StanCon, reminder also about my case study with simple visual illustrations users.aalto.fi/~ave/casestu...

users.aalto.fi

Laplace method and Jacobian of parameter transformation – Aki Vehtari

0174

Charles Margossian @charlesm993.bsky.social · 21/08/2026

📘 Reference manual: mc-stan.org/docs/referen... 📖 Case study: htmlpreview.github.io?https://gith... 📝 Technical details: - arxiv.org/abs/2306.14976 (arXiv '23) - arxiv.org/abs/2004.12550 (NeurIPS'20) 🌎 Open-source code: github.com/stan-dev/math

github.com

math/stan/math/mix/functor/laplace_marginal_density.hpp at develop · stan-dev/math

The Stan Math Library is a C++ template library for automatic differentiation of any order using forward, reverse, and mixed modes. It includes a range of built-in functions for probabilistic mode...

021

Charles Margossian @charlesm993.bsky.social · 21/08/2026

As of v2.39, Stan (@mc-stan.org) provides an embedded Laplace approximation for fitting latent Gaussian models. Thanks to the tremendous effort by Steve Bronder, @avehtari.bsky.social, @brianward.dev, and many others. 📽️ www.youtube.com/watch?v=DDTP... 🧵 1/

youtube.com

Charles Margossian - Embedded Laplace Approximation in Stan. StanCon 2026

YouTube video by Stan

182

Reposted by Charles Margossian

MC Stan @mc-stan.org · 20/08/2026

StanCon 2026 conference part is over and all the talks are available at StanCon 2026 playlist!

0145

Reposted by Charles Margossian

Aki Vehtari @avehtari.bsky.social · 20/08/2026

StanCon 2026 has been awesome! The talks are online, but it's been great to also have many discussions in person!

0171

Charles Margossian @charlesm993.bsky.social · 16/08/2026

✈️ Heading to StanCon'26! 🤝 Looking forward to connecting with colleagues, old and new. 🎙️ I'll give a talk Stan's new embedded Laplace approximation (mc-stan.org/docs/referen...), 📈 and a poster on an analysis of data from multiple clinical trials in Stan (arxiv.org/abs/2603.11019)

arxiv.org

Don't Disregard the Data for Lack of a Likelihood: Bayesian Synthetic Likelihood for Enhanced Multilevel Network Meta-Regression

Multilevel network meta-regression (ML-NMR) enables population-adjusted indirect treatment comparisons by combining individual patient data (IPD) with aggregate data. When individual-level covariates ...

050

Reposted by Charles Margossian

Aki Vehtari @avehtari.bsky.social · 13/08/2026

All four books I've co-authored are freely available online for non-commercial use: - Bayesian Workflow at avehtari.github.io/Bayesian-Wor... Links to other three books are in the quoted post 👇 (too many books to fit in one post!)

avehtari.github.io

Bayesian Workflow book: Website – Bayesian Workflow book

Website for the Bayesian Workflow book by Gelman, Vehtari, McElreath, et al. — case studies, code, and exercises in R and Stan.

8286134

Reposted by Charles Margossian

Aki Vehtari @avehtari.bsky.social · 14/07/2026

Finally, got a copy of Bayesian workflow book in my hand, and it looks awesome! I really like we did get full colors for figures, too

0505

Charles Margossian @charlesm993.bsky.social · 14/07/2026

This looks like a great opportunity. I think most people know what an outstanding stats department U Toronto has and on the basis of a visit, I can also attest to how congenial the researchers there are.

020

Reposted by Charles Margossian

Vianey Leos Barajas @vianeylb.bsky.social · 14/07/2026

My statistical sciences dept is hiring in the area of Statistical Learning Theory & adjacent fields (assistant professor rank). Located at downtown campus. 🔹Salary Range: $140,000-$190,000 annually (based on experience) 🔹Application Deadline: November 9, 2026 academicjobsonline.org/ajo/jobs/32307

academicjobsonline.org

University of Toronto, Statistical Sciences

Job #AJO32307, Assistant Professor, Statistical Learning Theory, Statistical Sciences, University of Toronto, Toronto, Ontario, CA

042

Charles Margossian @charlesm993.bsky.social · 03/07/2026

Catching up with a few co-authors of "Bayesian Workflow" and fellow Stan developers at #ISBA2026. @paulbuerkner.com @vianeylb.bsky.social @yulingy.bsky.social

192

Charles Margossian @charlesm993.bsky.social · 28/06/2026

🇯🇵 This week, I'm at the ISBA world meeting in Nagoya, Japan. 🤝 Looking forward to connecting with colleagues, old and new! 🎙️ I'll talk about MCMC on GPUs at the session on "Principled Tuning of MCMC" this Friday at 9am. 🪑 I'll chair the session on "Advances in Sampling" Friday at 11am.

040

Charles Margossian @charlesm993.bsky.social · 26/06/2026

🧑‍🏫 This has been a great first teaching experience. I had students from statistics but also from other departments (ecology, math, cs, econ) who brought their data and models, and were eager to use Bayesian workflow. 💡 My favorite part: discussing final projects with students during office hour!

020

Charles Margossian @charlesm993.bsky.social · 26/06/2026

The course was designed for grad students interested in doing research on the topic. ✨ Some highlights: - a dive in the theory of MCMC with an eye on how it informs methods, diagnostics and practice. - a detailed discussion of algorithms, including NUTS. - a running example from epidemiology

100

Charles Margossian @charlesm993.bsky.social · 26/06/2026

📘 With the release of our textbook "Bayesian Workflow" (avehtari.github.io/Bayesian-Wor...), I figured I'd also share the content of my graduate course on the topic at UBC. 🌎 charlesm93.github.io/stat547/ The course contains overlapping and complementary material, homeworks and reading.

avehtari.github.io

Bayesian Workflow book: Website – Bayesian Workflow book

Website for the Bayesian Workflow book by Gelman, Vehtari, McElreath, et al. — case studies, code, and exercises in R and Stan.

17419

Reposted by Charles Margossian

Aki Vehtari @avehtari.bsky.social · 20/05/2026

Stan embedded Laplace was a long project and happy that it's finally released. We are not competing with INLA and TMB software, as they are orders of magnitude faster and scale better with data size for models that you can implement with them 1/

1318

Reposted by Charles Margossian

Simons Foundation @simonsfoundation.org · 07/03/2026

#FlatironCCM's Teresa Huang explores how symmetries and structure can reveal new insights into the universe, aiding discovery in everything from cosmology to the development of fusion energy. www.simonsfoundation.org/teresa-hua…

simonsfoundation.org

Teresa Huang: Bridging Science and Machine Learning at Cosmic Scales

Flatiron Institute Research Fellow Teresa Huang uses machine learning to help scientists improve models for scientific applications involving large datasets.

052

Reposted by Charles Margossian

Sam Power @spmontecarlo.bsky.social · 05/03/2026

do mine eyes deceive me? a release date in the present year?

2242

Charles Margossian @charlesm993.bsky.social · 29/01/2026

StanCon 2026 is this August 17-21 in Upsala, Sweden 🇸🇪 www.stancon2026.org ⏰ Abstracts for contributed talks are due Feb 25 ⏰ Abstracts for posters are due May 27 And just to be clear: Yes, StanCon is my favorite conference to attend!! Can't wait for this one!

093

Reposted by Charles Margossian

Aki Vehtari @avehtari.bsky.social · 26/01/2026

Bayesian Workflow by Andrew Gelman, Aki Vehtari, @rmcelreath.bsky.social with @danpsimpson.bsky.social, @charlesm993.bsky.social, @yulingy.bsky.social, Lauren Kennedy, Jonah Gabry, @paulbuerkner.com, @modrakm.bsky.social, @vianeylb.bsky.social (in production, estimated copy-editing time 6 weeks)

**Part 1: From Bayesian inference to Bayesian workflow**

1. Bayesian theory and Bayesian practice
2. Statistical modeling and workflow
3. Computational tools
4. Introduction to workflow: Modeling performance on a multiple choice exam

**Part 2: Statistical workflow**

5. Building statistical models
6. Using simulations to capture uncertainty
7. Prediction, generalization, and causal inference
8. Visualizing and checking fitted models
9. Comparing and improving models
10. Statistical inference and scientific inference

**Part 3: Computational workflow**

11. Fitting statistical models
12. Diagnosing and fixing problems with fitting
13. Approximate algorithms and approximate models
14. Simulation-based calibration checking
15. Statistical modeling as software development

**4. Case studies**

16. Coding a series of models: Simulated data of movie ratings
17. Prior specification for regression models: Reanalysis of a sleep study
18. Predictive model checking and comparison: Clinical trial
19. Building up to a hierarchical model: Coronavirus testing
20. Using a fitted model for decision analysis: Mixture model for time series competition
21. Posterior predictive checking: Stochastic learning in dogs
22. Incremental development and testing: Black cat adoptions
23. Debugging a model: World Cup football
24. Leave-one-out cross validation model checking and comparison: Roaches
25. Model building and expansion: Golf putting
26. Model building with latent variables: Markov models for animal movement
27. Model building: Time-series decomposition for birthdays
28. Models for regression coefficients and variable selection: Student grades
29. Sampling problems with latent variables: No vehicles in the park
30. Challenge of multimodality: Differential equation for planetary motion
31. Simulation-based calibration checking in model development workflow

**Appendices**

A. Statistical and computational workflow for Bayesians and non-Bayesians
B. How to get the most out of Bayesian Data Analysis

315831

Charles Margossian @charlesm993.bsky.social · 08/01/2026

What is "workflow" and why is it important? The latest blog post by Andrew Gelman: statmodeling.stat.columbia.edu/2026/01/08/w...

statmodeling.stat.columbia.edu

What is “workflow” and why is it important? | Statistical Modeling, Causal Inference, and Social Science

010

Charles Margossian @charlesm993.bsky.social · 14/12/2025

🇪🇸 This week I'm attending ICSDS (International Conference on Stats & Data Science) in Sevilla, Spain. 🤝 Looking forward to connecting with colleagues, old and new! 💡On Wednesday, I'll give a talk on "Variational Inference in the Presence of Symmetry" at the 9 am session on Bayesian learning.

050

Reposted by Charles Margossian

Diana Cai @dianarycai.bsky.social · 04/12/2025

Check out my poster today (Thurs) at 11am--2pm session. Exhibit Hall C,D,E Poster Location: #602 "Fisher meets Feynman: score-based variational inference with a product of experts" (NeurIPS spotlight) with Robert Gower, David Blei, and Lawrence Saul @flatironinstitute.org #NeurIPS2025

2234

Charles Margossian @charlesm993.bsky.social · 07/11/2025

Details and Q&A for applications: www.stat.ubc.ca/graduate-adm...

stat.ubc.ca

Graduate Admissions | UBC Statistics

000

Charles Margossian @charlesm993.bsky.social · 07/11/2025

Applications for the PhD and MSc programs in statistics at UBC are now open! 📆 Deadline for PhD program is December 1st 📆 Deadline for MSc program is January 5th The department covers all areas of statistics and we have a lot of momentum in Bayesian computation!

2105

Charles Margossian @charlesm993.bsky.social · 17/09/2025

Application for a postdoc research fellowship in computational mathematics at the Flatiron Institute in New York are now open! apply.interfolio.com/173401 📆 Deadline is December 1st. 🔭 This is an excellent place to do research at the interface of ML, stats and the natural sciences.

apply.interfolio.com

Apply - Interfolio {{$ctrl.$state.data.pageTitle}} - Apply - Interfolio

111

Charles Margossian @charlesm993.bsky.social · 10/09/2025

I also like to describe this paper as a discussion on what is the best circle to approximate an ellipse :) 🧵 4/4

000

Charles Margossian @charlesm993.bsky.social · 10/09/2025

This paper contributes to the foundational theory of VI, and dives deep into both conceptual and practical questions such as: How do we measure uncertainty in high-dimensions? How should we measure discrepancy between probability distributions? 🧵 3/

100

Charles Margossian @charlesm993.bsky.social · 10/09/2025

The two main results of the paper are: 1️⃣ An impossibility theorem that shows that any factorized (mean-field) approximation of VI can at beast learn one of three measures of uncertainty 2️⃣ An ordering of divergences used as objectives for VI based on the uncertainty in their approximation. 🧵 2/

100

Charles Margossian @charlesm993.bsky.social · 10/09/2025

My paper with Loucas Pillaud-Vivien and Lawrence Saul, “Variational Inference for Uncertainty Quantification: An Analysis of Trade-offs”, has been accepted for publication in the Journal of Machine Learning Research. 📃 arxiv.org/abs/2403.13748 🧵 1/

1165

Charles Margossian @charlesm993.bsky.social · 01/08/2025

Yes, in principle, I start at UBC Statistics today. But right now, I'm running around the Frankfurt airport to catch my flight to Vancouver .... 🏃‍♂️🧳✈️ www.stat.ubc.ca/news/charles...

stat.ubc.ca

Charles Margossian Joins the UBC Department of Statistics | UBC Statistics

030

Charles Margossian @charlesm993.bsky.social · 28/07/2025

💻 This was also my first time using Stan playground (github.com/flatironinst...) to teach a class! Thank you Brian Ward for creating this tool and helping me set it up for the class!

github.com

GitHub - flatironinstitute/stan-playground: Run Stan models in the browser

Run Stan models in the browser. Contribute to flatironinstitute/stan-playground development by creating an account on GitHub.

095

Charles Margossian @charlesm993.bsky.social · 28/07/2025

📔 My course: "Bayesian Statistics: a practical introduction." We covered Bayesian models (priors and likelihoods), Markov chain Monte Carlo and uncertainty aware cross-validation. Most of our discussion was motivated by an example from epidemiology.

120

Charles Margossian @charlesm993.bsky.social · 28/07/2025

Earlier this month, I taught at the summer school on "cryptography, statistics and machine learning" (mathschool.ysu.am) hosted by Yerevan State University in Armenia 🇦🇲 🙏 Thank you to the organizers for putting together such a wonderful event! I truly enjoyed interacting with the students.

171

Charles Margossian @charlesm993.bsky.social · 26/06/2025

👨‍💻 Credit also to Brian Ward and Steve Bronder for their contribution to the C++ implementation and integration with the Stan ecosytem. (From what I understand, WALNUTS is not part of the next Stan release but you can use it on models written in Stan!!)

000

Charles Margossian @charlesm993.bsky.social · 26/06/2025

New manuscript by Nawaf Bou-Rabee, Bob Carpenter, Tore Kleppe and Sifan Liu on the WALNUTS algorithm which improves of the NUTS sampler by introducing a locally adaptive step size. 📜 Paper: arxiv.org/pdf/2506.18746 💻 Code: github.com/bob-carpente...

2136

Charles Margossian @charlesm993.bsky.social · 15/06/2025

🇸🇬 Next stop: Singapore for BayesComp'25 (bayescomp2025.sg) The organizers put together a wonderful program! I'll be: 🪑 chairing the session on "Parallel comp for MCMC" 🎙️ speaking at the session on "Advances in VI" Looking forward to meeting researchers and catching up with colleagues.

082

Charles Margossian @charlesm993.bsky.social · 13/06/2025

Research opportunity for a graduate student in ecology 🌳 at UBC 🇨🇦 with Lizzie Wolkovich and the Temporal Ecology lab (temporalecology.org). 📝 Apply here: temporalecology.org/joining-the-... by July 1st 2025! The abstract sounds fascinating (see attached).

002

Charles Margossian @charlesm993.bsky.social · 09/06/2025

🧑‍💻 Candidate release for Stan 2.37 is out: discourse.mc-stan.org/t/cmdstan-st.... Lots of exciting features to try out, including: - embedded/integrated Laplace approximation - new constrained types (e.g. sum_to_zero_matrix) - built-in constraint transformations exposed

discourse.mc-stan.org

CmdStan & Stan 2.37 release candidate

I am happy to announce that the latest release candidates of CmdStan and Stan are now available on Github! This release cycle brings the embedded Laplace approximation, a sum-to-zero matrix type, new...

031

Reposted by Charles Margossian

Andrew Gelman et al. @statmodeling.bsky.social · 27/05/2025

Taking our Models Seriously (my talk at StanBio Connect, this Friday 9am) statmodeling.stat.columbia.edu/2025/05/27/t...

statmodeling.stat.columbia.edu

Taking our Models Seriously (my talk at StanBio Connect, this Friday 9am) | Statistical Modeling, Causal Inference, and Social Science

042

Charles Margossian @charlesm993.bsky.social · 05/05/2025

🙏This award is this much more meaningful to me in that it celebrates my collaboration with the amazing Lawrence Saul (users.flatironinstitute.org/~lsaul/).

000

Charles Margossian @charlesm993.bsky.social · 05/05/2025

💡We provide theory on VI's ability to recover certain statistics, despite misspecification---that is in settings where we do NOT drive the KL-divergence to 0. 👉 VI is provably good at recovering the mean and correlation matrix.

100