R-folks, is the RTMB package the go-to autodiff package in R now? Limitations? Fast? Alternatives? #RStats #r4ds

Uncertainty in the LLM era - Science, more than scale speakerdeck.com/gaelvaroquau... My #EurIPS keynote, on scale, uncertainty, and narratives in AI

My baby #JuliaLang package got an award! DifferentiationInterface.jl just received a national prize for open-source research software and I couldn't be prouder. We started this from a vague dream with @adrianhill.de, and reached 1000 dependents and 100k downloads last month. Research != just papers.

We are recruiting a PhD student at Chalmers University of Technology, Gothenburg, Sweden. The project explores Bayesian Experimental Design for real-time, risk-aware trajectory planning in autonomous driving, combining Bayesian inference and optimal control Apply by November 30 tinyurl.com/4mr6u79y

Do this, if you can! Your work will reach thousands of thankful Bayesians.

Photo of me after an intensive Bayes lecture at the blackboard.

Very nice 70 page intro to Julia in these notes. Well done!

Julia v1.12 is out 🎈🙃 #JuliaLang discourse.julialang.org/t/julia-v1-1...

Great to see the forecast package from R in native Julia. One less use case for RCall.jl in my workflow.

This is a wonderful side-by-side comparison!

So me and my buddy chatGPT are now into using Lua filters in the Quarto YAML to hook into the pandoc AST to modify the inline LaTeX at compile time to convert LaTeX syntax to things that render correctly to html. It works, that is all I can tell you.

"Spotify for Linux is a labor of love from our engineers that wanted to listen to Spotify on their Linux development machines. They work on it in their spare time and it is currently not a platform that we actively support." Honest, but weird when you have the money and passionate people. #linux

We also wish a pleasant weekend to the couriers who transform our parcels in their own way, #stats!

An excellent way to feel like a complete loser is to try to do something semi-advanced with LaTeX. It is also a great way to waste an afternoon.

If you're interested in learning #JuliaLang and are currently an #RStats user (or even if you're not!), then here's a little introduction to getting started! 📊 Blog post: nrennie.rbind.io/blog/introdu... #QuartoPub #Julia @tidierjl.bsky.social

My Bayesian Data Analysis course at Aalto is starting in 20mins. There are now 375 registered students, but as the course is not compulsory for most, I expect about 230 students to finish it. All the course material is available online at avehtari.github.io/BDA_course_A...

Dusting of my old Lenovo ThinkPad X220, bought 14 years ago. Still snappy after a fresh Linux install! #linux

Hmm, I can't quite pin it down, but something seems missing here?

Remember to follow the official rebuttal guide.

Yes, the interoperability between Julia and many other languages is amazing! I often work in the other direction, calling for example these from within Julia code: - R (github.com/JuliaInterop...) - Python (github.com/JuliaPy/PyCa...) - Matlab (github.com/JuliaInterop...) from Julia. #julialang

Contemplating starting a side business where I make academics' #rstats ggplot charts non-ugly for $25 a pop.

RCall.jl is really useful. Take any function that you like from R and turn into a Julia function without any hassle. I use this a lot when benchmarking my research coded in Julia with established methods in R.

Hello Friends! I'm on the job market now! I have a oodles of knowledge for all the software performance engineering tricks in Rust, Julia and other systems languages and would love to work with teams that are looking to skill up in those respects, from back ends to big data crunching!

Amazing run-through, from new packages all the way down to the bare compiled metal. Everyone knows this, but still: @chrisrackauckas.bsky.social is an amazing talent in explaining complicated technical details with such ease, knowledge, enthusiasm and wit. Brilliant! youtube.com/watch?v=17aN...

Data Science/ML/Stats academics: We are hiring a senior lecturer to contribute to research and the new (hugely popular) master's in Data Science, Statistics and Decision Analysis: bit.ly/3GZj0N9 Excellent job security, health care, pensions and all that. Reposts appreciated! bit.ly/435VTYW

A wonderful upcoming Turing.jl talk: github.com/TuringLang/T... This is part of learnbayes.se with seminars from Andrew Gelman, Frank Harrell and Aki Vehtari and more. Bayes and Julia, the best things in life are free! #julialang

Want to participate in #TidyTuesday but #julialang is more your speed? Check out #TidierTuesday! github.com/TidierOrg/Ti... Big shout out to @jonthegeek.com , @frankiethull.bsky.social , and the folks behind @tidierjl.bsky.social for their work making this happen.

Why choose between Julia and R when you can use both? With RCall.jl, you can tap into R’s ecosystem—like classInt—directly from Julia. Learn how to bridge both worlds and expand your analytical toolbox: medium.com/@technocrat/... #JuliaLang #DataScience #RStats #Interop #programming #analytics

Took me many years before I learned the \phantom command in LaTeX, and its precision still brings me joy. 'The \phantom command creates a box with the same height, depth, and width as subformula, but empty.' latexref.xyz/_005cphantom...

I know, it's only Taylor approximations (but I like it). observablehq.com/@mattiasvill...

This sounds interesting for those in the area #julialang

Such wonderful summary of what is going on in #julialang!

Fellow #JuliaLang enthusiasts, here's your chance to shine: the call for proposals of JuliaCon Local Paris 2025 is finally open. Send us your coolest, nerdiest contributions and we'll prepare a scientific program for the ages! pretalx.com/juliacon-loc...

@googlecolab.bsky.social now has native support for #JuliaLang! 🎉 No special setup is needed anymore—start coding and sharing your @julialang.org projects! 🚀

Turing.jl announced they are releasing a fortnightly series of updates. First one came out last week. Updates for defining models, automatic differentiation, and sub-models. Take a read: turinglang.org/news/posts/2... Future updates are also being pushed to a github issue. #JuliaLang #Bayesian #PPL

There is a nice episode of the Julia Dispatch podcast that talks about some of these issues: youtu.be/slDh2HxTzt4?...

This looks amazing! #julialang

Immensely sad that Herman has passed away. He took me into the Bayesian community at the Valencia meeting in 1998. Very encouraging discussant of my thesis. Always helping the younger and willing to share his time and knowledge. He will be missed by many. Obituary: esobe.org/Herman_van_D...

Wikipedia is the internet at its best. If you can, please consider donating at: donate.wikimedia.org/wiki/Special...

Contribute to open-source with #SciML Small Grants! Work on exciting projects like NeuralPDE updates, benchmark refactors, and more—all while getting paid. sciml.ai/small_grants... #JuliaLang #OpenSource #SoftwareDevelopment

Illustration of linear regression with time-varying parameters. observablehq.com/@mattiasvill...

Wrote a basic tutorial about state-space models and Kalman filtering, sprinkled with interactivity, for an intermediate stats course. statisticssu.github.io/STM/tutorial...

Mixture of Gaussians #observablehq observablehq.com/@mattiasvill...

Bayesian analysis of Multinomial data using a Dirichlet prior with javascript in observablehq.com observablehq.com/@mattiasvill...

Trying to guide my students in a first course in stats (SDA1) on how to choose a distribution depending on properties of the data (among the ones covered by our triplet of basic courses SDA1-3).

Very happy to have Antonietta Mira visiting our department on October 20! All welcome!

Wrote a tutorial for a basic course on how to compute maximum likelihood estimators with approximate standard errors in R. Sprinkled with some #observablehq interactivity. statisticssu.github.io/STM/tutorial...

Yes, couldn't agree more. Too much knowledge are being put behind paywalls and University educational platforms.