Kevin Han Huang

Acknowledgement: This workshop is generously supported by Centre for Research in Statistical Methodology (CRiSM) at @warwickstats.bsky.social and Prob_AI Hub.

Registration is open until 31 March on a first-come-first-serve basis: warwick.ac.uk/fac/sci/stat... (4/4)

Suitable for PhD students and researchers with graduate-level background in probability, statistics, ML theory or other related mathematical disciplines. No prior knowledge on scaling law required. (3/4)

Themed around the theoretical understanding of scaling laws for large neural networks, the workshop covers both introductory tutorials and talks on latest research advances. Confirmed speakers include Blake Bordelon, Leena C Vankadara, Lénaïc Chizat, Mufan Li and Sam Smith.
(2/4)

Very excited to announce the ProbAI Theory of Scaling Laws Workshop (warwick.ac.uk/fac/sci/stat...) at @warwickstats.bsky.social, 22-24 June! (1/4)

🔥 WANTED: Student Researcher to join me, @vdebortoli.bsky.social, Jiaxin Shi, Kevin Li and @arthurgretton.bsky.social in DeepMind London.

You'll be working on Multimodal Diffusions for science. Apply here google.com/about/career...

Thanks Ray!!

Thank you Pierre!!

A better photo, in retrospect! 😄

Didn’t even realise Singapore bus stops have small plantations on top… all the little things one missed paying attention to as a kid :’)

Singaporean owls out at day time?

Last but not least of my travel updates: Courtesy of the very kind @slchau.bsky.social, I'm giving a talk at 14:30, 27 Jun
@NTU CCDS in SG on data augmentation & Gaussian universality, which strings together several works over my PhD.

If you're in SG/Lyon over the next few weeks, let me know! :)

Universality of High-Dimensional Logistic Regression and a Novel CGMT under Dependence with Applications to Data Augmentation Over the last decade, a wave of research has characterized the exact asymptotic risk of many high-dimensional models in the proportional regime. Two foundational results have driven this progress: Gau...

Meanwhile, excited to be in #Lyon for #COLT2025, with a co-first author paper (arxiv.org/abs/2502.15752) with the amazing team -- Matthew M Mallory and our advisor Morgane Austern!

Keywords: Gaussian universality, dependent data, convex Gaussian min-max theorem, data augmentation!

Diagonal Symmetrization of Neural Network Solvers for the Many-Electron Schrödinger Equation Incorporating group symmetries into neural networks has been a cornerstone of success in many AI-for-science applications. Diagonal groups of isometries, which describe the invariance under a simultan...

Sadly missing ICML due to visa :'(, but looking forward to share our ICML paper (arxiv.org/abs/2502.05318) as a poster at #BayesComp, Singapore!

Work on symmetrising neural nets for schrodinger equation in crystals, with the amazing Zhan Ni, Elif Ertekin, Peter Orbanz and Ryan P. Adams

Formalizing a proof in Lean using Github copilot and canonical YouTube video by Terence Tao

As an experiment, I tried to use automated tools to formalize (in as "mindless" a fashion as possible) a one-page human written proof into Lean. You can watch the results here: www.youtube.com/watch?v=cyyR...

📣 In view of the current geopolitical landscape, the Dame Kathleen Ollerenshaw (DKO) Fellowships call could be your ticket to move to Manchester. Come join the AI FUN at the Manchester Centre for (AI FUN)damentals.

Deadline: 7 April 2025⌛️
👉 www.jobs.manchester.ac.uk/Job/JobDetai...

We’re thrilled to announce the recipients of the inaugural David Cox Medal for Statistics

🏅 Prof Richard Samworth
🏅 Prof Eric Tchetgen Tchetgen
🏅 Prof Nancy Zhang @nancyrzhang.bsky.social

Read more: rss.org.uk/news-publica...

Kevin Huang (@kevhhuang.bsky.social) will talk about “Diagonal Symmetrization of Neural Network Solvers for the Many-Electron Schrödinger Equation” at the Jump Trading/@ucl-csml-ellis.bsky.social seminar. Don't miss it!

📆 Fri Mar 21, noon UK time
🗺️ Hybrid
ℹ️ ucl-ellis.github.io/jt_csml_semi...