Alex Thiery

@roydanroy @ShriramKMurthi There's a really wonderful lecture series on YouTube of McKays information theory. It makes it really easy to dive in! youtube.com/playlist?list=…

For a higher number of vertices:

Mean-Field Potts model: 1st order phase transition

@ano2math5 😅 😅 👍

@alexxthiery Thank you Alex! I wrote it as if it were a love letter to you 😉

Proposing a high-dimensional asymptotic analysis framework for PDMP efficiency comparison 1. Derive diffusion approximation for various PDMP samplers 2. Compare the time scaling (≒ the scaling of computational complexity) required to obtain the limit 3. If the scaling is identical, compare the speed of the diffusion

Lots of fun learning how to use @claudeai code, it took ~100 steps & several agents to build a human-like solution to that (very difficult) sudoku. Anybody managed to do that for chess tactics?

Start-of-the-semester survey to a ML class: non AI-assisted coding is dead 👍

@docmilanfar Diffusion models without measure theory?

yet another year gone by and I've not used measure theory

🔥 WANTED: Student Researcher to join me,@ValentinDeBort1,@thjashin,@liwenliang,@ArthurGretton in DeepMind London. You'll be working on Multimodal Diffusions for science. Apply here google.com/about/careers/…

I'm teaching Bayesian Optimization for the first time this semester, so finally had to implement it myself. Fun stuff, with a few gotchas along the way!

Art B. Owen. [math.ST]. Better bootstrap t confidence intervals for the mean. arxiv.org/abs/2508.10083

I'm looking for talented and ambitious PhD students to join me at Nanyang Technological University Singapore to work on safe and robust AI systems! Full scholarships covering tuition and a stipend are available, and are open to local and international students alike.

@hayou_soufiane @JohnsHopkins Beautiful news, congrats!

Career update: happy to share that I'm joining @JohnsHopkins as Asst Professor with a joint appointment in the dept of Applied Mathematics and Statistics (AMS) and the Data Science and AI Institute (DSAI). PhD/Postdoc positions in my lab will be announced soon!

@kfountou arxiv.org/abs/1306.3039

This is the second-best paper I have ever read. It combines random walks, group theory, and representation theory. It's amazing how two people managed to combine so many difficult topics into one clean paper.

@sirbayes @docmilanfar 🤣

@docmilanfar It’s real, You can check this for yourself. I’ll make sure not to read these. Can we auto black list the authors?

This isn’t surprising anymore, but it should be shocking.

@xuanalogue Welcome to @NUSingapore 🎉

I've struggled to announce this amidst so much dark & awful going on in the world, but with 1mo to go, I wanted to share that: (i) I finally graduated; (ii) In August, I'll begin as an assistant professor in the CS dept. of the National University of Singapore.

@cambUP_maths x.com/StatsPapers/st…

Scalable Monte Carlo for Bayesian Learning by Professor Paul Fearnhead, Dr Christopher Nemeth, Professor Chris J. Oates and Dr Chris Sherlock A clear and intuitive introduction to advanced topics in Markov chain Monte Carlo, with a focus on scalability. 📚 cup.org/4l42JW8

@JFPuget @ChShersh Call E(k) the expected value of the same game, but with k trials in total. In the original game, if k trials remain and the current value v is < E(k), one should reroll. So we need to compute E(k), which can be done by induction starting from E(1)=0.5, E(2)=5/8, etc..

@alexxthiery @ChShersh You're saying that I should replace 1/2 by the expectation computed that way for the remaining k tries?

Quant interview question: You press a button that gives your randomly uniformly distributed number between $0 and $100K Each time you press, you have two choices: 1. Stop and take this amount of money 2. Try again You can try 10 times total. When do you stop?