new preprint with the amazing Luca Viano and Gergely Neu on offline imitation learning! when the expert is hard to represent but the environment is simple, estimating a Q-value rather than the expert directly may be beneficial. there are many open questions left though!

wanna know how to do inverse Q-learning right? read this paper then!! joint work with the best team of students ever ♥️

New preprint out on arXiv: "Self-Supervised Evolution Operator Learning for High-Dimensional Dynamical Systems"! Read it here: pietronvll.github.io/encoderops/

New paper on Stationary MMD points 📣 arxiv.org/pdf/2505.20754 1️⃣ Samples generated by MMD flow exhibit 'super-convergence' 2️⃣ A discrete-time finite-particle convergence result for MMD flow Joint work with Toni Karvonen, Heishiro Kanagawa, François-Xavier Briol, Chris J. Oates

Very much looking forward to this ! 🙌 Stellar line-up

Dimitri Meunier, Antoine Moulin, Jakub Wornbard, Vladimir R. Kostic, Arthur Gretton. [stat.ML]. Demystifying Spectral Feature Learning for Instrumental Variable Regression. arxiv.org/abs/2506.10899…

This has been a long time coming! Really happy to announce Aeon, the culmination of my main Ph. D. work! A true everything platform for behavioral / systems / computational neuroscience

I’ll be speaking at ENUMATH conference (Sep 1st - Sep 5th) in Heidelberg at the “Approximation Theory meets Statistical Learning” minisymposium organized by Nicola Rares Franco, Nick Nelsen and Simone Brugiapaglia. Let’s grab a coffee if you’re there!

The tradition of tea time talks started long, long ago, and came to Alberta from the Gatsby unit (Neuroscience) at University College London.

Last call to register at mmlworkshop.ethz.ch for the Math for Trustworthy ML workshop in Switzerland with the possibility to present your own work as poster/talk, we still have a few slots left!

I'm thrilled to announce that my #ERCStG project **Optinfinite : Efficient infinite-dimensional optimization over measures** has been accepted. Thank you European Research Council (ERC) ! Many thanks also to CREST (UMR 9194) Institut Polytechnique de Paris for their support, as well as to my collaborators and friends.

Accepted as a spotlight paper at NeurIPS - catch you in San Diego!

ICLR 2026 What to do when hours before the rebuttal deadline a clearly fully LLM review with obvious hallucinations was changed parroting other ones? When the rebuttal started we notified AC, the reply: I will consider this when making the decision, please reply to it as you see fit

There is a serious issue here ICLR 2026 , reviewers can entirely over-write their review following the warning. This happened to us today as we were submitting our answers. Openreview does not even send a notification that a change to the review has been made.

Lol LLM reviewers secretly updating their review after the ICLR post announcing sanctions is really sneaky ML conferences should have ban policies like TMLR does

Proud to share our new NPIV paper! 🎉 Observed covariates make this problem far trickier. Amazing leadership from Steve & Hudson in nailing the theory. Check it out! 👇

Heading to San Diego to present the spotlight paper "Regularized least squares learning with heavy-tailed noise is minimax optimal" - joint work with Nic Mücke 🦩 🇪🇺, Dimitri Meunier and Arthur Gretton. Wednesday 16:30-19:30, Exhibit Hall C,D,E #3012, come by and say hi! :D