I defended my PhD last week ✨ Huge thanks to: • My supervisors @paulbuerkner.com @stefanradev.bsky.social @avehtari.bsky.social 👥 • The committee @ststaab.bsky.social @mniepert.bsky.social 📝 • The institutions @ellis.eu @unistuttgart.bsky.social @aalto.fi 🏫 • My wonderful collaborators 🧡 #PhDone 🎓

What advice do folks have for organising projects that will be deployed to production? How do you organise your directories? What do you do if you're deploying multiple "things" (e.g. an app and an api) from the same project?

Amortized inference for finite mixture models ✨ The amortized approximator from BayesFlow closely matches the results of expensive-but-trustworthy HMC with Stan. Check out the preprint and code by @kucharssim.bsky.social and @paulbuerkner.com👇

Finite mixture models are useful when data comes from multiple latent processes. BayesFlow allows: • Approximating the joint posterior of model parameters and mixture indicators • Inferences for independent and dependent mixtures • Amortization for fast and accurate estimation 📄 Preprint 💻 Code

If you know simulation based calibration checking (SBC), you will enjoy our new paper "Posterior SBC: Simulation-Based Calibration Checking Conditional on Data" with Teemu Säilynoja, @marvinschmitt.com and @paulbuerkner.com arxiv.org/abs/2502.03279 1/7

A study with 5M+ data points explores the link between cognitive parameters and socioeconomic outcomes: The stability of processing speed was the strongest predictor. BayesFlow facilitated efficient inference for complex decision-making models, scaling Bayesian workflows to big data. 🔗Paper

Join us this Thursday for a talk on efficient mixture and multilevel models with neural networks by @paulbuerkner.com at the new @approxbayesseminar.bsky.social!

Paul Bürkner (TU Dortmund University), will give our next talk. This will be about "Amortized Mixture and Multilevel Models", and is scheduled on Thursday the 30th January at 11am. To receive the link to join, sign up at listserv.csv.warwick...

Paul Bürkner (@paulbuerkner.com) will talk about amortized Bayesian multilevel models in the next Approximate Bayes Seminar on January 30 ⭐️ Sign up to the seminar’s mailing list below to get the meeting link 👇

More than 60 German universities and research outfits are announcing that they will end their activities on twitter. Including my alma mater, the University of Münster. HT @thereallorenzmeyer.bsky.social nachrichten.idw-online.de/2025/01/10/h...

what are your best tips to fit shifted lognormal models (in #brms / Stan)? I'm using: - checking the long tails (few long RTs make the tail estimation unwieldy) - low initial values for ndt - careful prior checks - pathfinder estimation of initial values still with increasing data, chains get stuck

OK, here is a very rough draft of a tutorial for #Bayesian #SEM using #brms for #rstats. It needs work, polish, has a lot of questions in it, and I need to add a references section. But, I think a lot of folk will find this useful, so.... jebyrnes.github.io/bayesian_sem... (use issues for comments!)

Ternary plots to represent data in a simplex, yay or nay? #stats #statistics #neuroscience

Writing is thinking. It’s not a part of the process that can be skipped; it’s the entire point.

1️⃣ An agent-based model simulates a dynamic population of professional speed climbers. 2️⃣ BayesFlow handles amortized parameter estimation in the SBI setting. 📣 Shoutout to @masonyoungblood.bsky.social & @sampassmore.bsky.social 📄 Preprint: osf.io/preprints/ps... 💻 Code: github.com/masonyoungbl...

Neural superstatistics are a framework for probabilistic models with time-varying parameters: ⋅ Joint estimation of stationary and time-varying parameters ⋅ Amortized parameter inference and model comparison ⋅ Multi-horizon predictions and leave-future-out CV 📄 Paper 1 📄 Paper 2 💻 BayesFlow Code

“We don’t value software, data, and methods in the same way we value papers, even though those resources empower millions of scientists” 💯 www.statnews.com/sponsor/2024...

The public beta version of Positron was released almost 6 months ago, and the team certainly hasn’t been idle! So what happened over the last half year? Is it worth switching? 👀 I definitely like where it's heading! Personal highlights: data explorer, command palette, help on hover + extensions 👇🏻📚

I'm going to have time to do 1-2 contributions for the summer 25 release. Here's my list to choose from, what is most interesting to you? - adding lower/upper bounds to ordered vectors (removing positive ordered since it's achieved by lb=0)

Prior specification is one of the hardest tasks in Bayesian modeling. In our new paper, we (Florence Bockting, @stefanradev.bsky.social and me) develop a method for expert prior elicitation using generative neural networks and simulation-based learning. arxiv.org/abs/2411.15826

I'm writing up a brief history of the tidyverse? What do you want to know about it? #rstats

Any single analysis hides an iceberg of uncertainty. Sensitivity-aware amortized inference explores the iceberg: ⋅ Test alternative priors, likelihoods, and data perturbations ⋅ Deep ensembles flag misspecification issues ⋅ No model refits required during inference 🔗 openreview.net/forum?id=Kxt...

I feel like not enough people know about Quarto for creating documents. How it works: Write in markdown and use Quarto to convert it to html, pdf, epub, ... I produce my books with Quarto (web + ebook + print version). But you can also use it for websites, reports, dashboards, ... quarto.org

Optimist: The cup is half full Pessimist: The cup is half empty Frequentist: *takes a deep breath* The probability that the cup is half full given the observed volume of water (or more extreme volumes) is larger than 5% so I cannot reject the null hypothesis that the cup is half full.

Optimist: the cup is half full Pessimist: the cup is half empty Comparative cognition researcher: I wonder if this animal will drop some stones into this cup

Ladies and gentlemen... the weekend. (also: you are important and are not alone 🧡)

BayesFlow is a library for amortized Bayesian inference with neural networks. ⋅ Multi-backend via Keras 3: Use PyTorch, TensorFlow, or JAX. ⋅ Modern nets: Flow matching, diffusion, consistency models, normalizing flows, transformers ⋅ Built-in diagnostics and plotting 🔗 github.com/bayesflow-or...

The ✨ML Internship Feed✨ is here! @serge.belongie.com and I created this feed to compile internship opportunities in AI, ML, CV, NLP, and related areas. The feed is rule-based. Please help us improve the rules by sharing feedback 🧡 🔗 Link to the feed: bsky.app/profile/did:...

The brand new `legendry` package by @teunbrand.bsky.social takes ggplots2 guides to the next level 🤩 teunbrand.github.io/teunbrand_bl...

I created two starter packs for Women in AI, as the first filled up 😎 I really hope I’ve added everyone who’s asked to be added, but let me know if you don’t see yourself. Nominations also welcome! go.bsky.app/LaGDpqg go.bsky.app/2wr669L

Just coming back from an interdisciplinary retreat, and it's kind of crazy how many different ways there are to write down the same linear regression problem.

The beta version of BayesFlow 2.0 is becoming more powerful and stable by the day. If you are curious about Amortized Bayesian Inference, give BayesFlow a try! github.com/bayesflow-or...

I got a Probabilistic Programming starter pack going. Hit me up if you're involved with #probprog R&D and want in! go.bsky.app/JfvubEf

We are organising the First International Conference on Probabilistic Numerics (ProbNum 2025) at EURECOM in southern France in Sep 2025. Topics: AI, ML, Stat, Sim, and Numerics. Reposts very much appreciated! probnum25.github.io

We strongly suggest that academic publishers and other platforms that host research rapidly implement a Share to Bluesky button for their articles. Here's how: docs.bsky.app/docs/advance... #AcademicSky #HigherEd #Altmetrics

This predated the X-odus, so I thought I'd bump it. #rstats brms is a fantastic tool that has made it so much easier to work with Bayesian models. And to teach - I'm going to introduce my stats students to the concepts this week and have them dive right in and start fitting models.

I made one for stats papers

I'd love to include a bunch of examples of what you can use LLMs for in the elmer documentation to inspire #rstats developers? What cool tools have you used or created? (Bonus points if they have public R code I can link to).

I created a starter pack of scientists in the European Laboratory for Learning and Intelligent Systems (ELLIS) 🇪🇺 Please ping me and I‘ll add you. go.bsky.app/Cihupkk

Seeing all my old friends on here again

I wrote a thing. I think Bluesky is the future of Twitter, and that's a good thing in large part b/c of the team behind it, and opined on the future of the social interest graph medium.com/@AlexCartaz/...

When I came here to 🦋 last year it was a ghost town for so long. Now it finally feels like maybe I have an online #AcademicSky network to chat with again! I’m just realizing how much of a hole leaving that on X left in my life.

It feels that the longer I do statistics, the harder it becomes. I never get an analysis just "right". There is always one more assumption to change or one more term to add to my model.

FWIW, I've recently spent a ton of time working to improve `tinyplot` with Grant and Achim. The upcoming version is going to be amazing. Ultra-concise syntax for all the common plots, with auto legend, groups, and facets. 0-dep. For interactive use and teaching, this is going to be great.

I am not usually a fan boy of anything, but I must say the new Linkin Park album makes me feel weirdly excited! A lot of good teenage memories come to mind.

Want to add a Bluesky icon to your #Quarto site? 🦋 • Install quarto-iconify: github.com/mcanouil/qua... • Add as 'text' - text: "{{< iconify simple-icons bluesky >}}" href: bsky.app/profile/ivel... Example code: github.com/ivelasq/pipe... Related GH link: github.com/quarto-dev/q...

I don’t care if you have many followers or (still) get a lot of engagement on Xitter In today’s age, continuing to post content to this rotten platform is helping legitimizing a massive and brutal attack against democracy itself It’s time to leave Many of us did, and we turned out more than fine

tags for the tag god! #stats 🧪

brms book update: I have added a new chapter on generalized linear multilevel models (GLMMs). See paulbuerkner.com/software/brm... for the latest draft of the book. I would love to hear your thoughts!