Thank you for a fantastic conference!

Sequential kernel embedding for mediated and time-varying dose response curves Appearing in Bernoulli: projecteuclid.org/journals/ber... with preprint here: arxiv.org/abs/2111.03950 ...along with code! github.com/liyuan9988/K... Rahul Singh, Liyuan Xu

Research Fellow position open at @gatsbyucl.bsky.social to work with me and Jason Hartford on Causality in Biological Systems! Apply at link, deadline is 27 August: www.ucl.ac.uk/work-at-ucl/...

Accelerated Diffusion Models via Speculative Sampling, at #icml25 ! 16:30 Tuesday July 15 poster E-3012 arxiv.org/abs/2501.05370 @vdebortoli.bsky.social Galashov @arnauddoucet.bsky.social

Distributional diffusion models with scoring rules at #icml25 Fewer, larger denoising steps using distributional losses! Wednesday 11am poster E-1910 arxiv.org/pdf/2502.02483 @vdebortoli.bsky.social Galashov Guntupalli Zhou @sirbayes.bsky.social @arnauddoucet.bsky.social

Distributional Reduction paper with H. Van Assel, @ncourty.bsky.social, T. Vayer , C. Vincent-Cuaz, and @pfrossard.bsky.social is accepted at TMLR. We show that both dimensionality reduction and clustering can be seen as minimizing an optimal transport loss 🧵1/5. openreview.net/forum?id=cll...

Composite Goodness-of-fit Tests with Kernels, now out in JMLR! www.jmlr.org/papers/v26/2... Test if your distribution comes from ✨any✨ member of a parametric family. Comes in MMD and KSD flavours, and with code. @oscarkey.bsky.social @fxbriol.bsky.social Tamara Fernandez

Turns out that overfitting is the right approach when you want to generalize to new tasks!

Mattes Mollenhauer, Nicole M\"ucke, Dimitri Meunier, Arthur Gretton: Regularized least squares learning with heavy-tailed noise is minimax optimal https://arxiv.org/abs/2505.14214 https://arxiv.org/pdf/2505.14214 https://arxiv.org/html/2505.14214

Looking forward to this!

Kernel Single Proxy Control for Deterministic Confounding at #AISTATS25 Proxy causal learning generally requires two proxy variables - a treatment and an outcome proxy. When is it possible to use just one? arxiv.org/abs/2308.04585 Liyuan Xu

Credal Two-Sample Tests of Epistemic Uncertainty at #AISTATS25 Compare credal sets: convex sets of prob measures where elements capture aleatoric uncertainty; set represents epistemic uncertainty. arxiv.org/abs/2410.12921 @slchau.bsky.social Schrab @sejdino.bsky.social @krikamol.bsky.social

Spectral Representation for Causal Estimation with Hidden Confounders at #AISTATS2025 A spectral method for causal effect estimation with hidden confounders, for instrumental variable and proxy causal learning arxiv.org/abs/2407.10448 Haotian Sun, @antoine-mln.bsky.social, Tongzheng Ren, Bo Dai

Density Ratio-based Proxy Causal Learning Without Density Ratios 🤔 at #AISTATS2025 An alternative bridge function for proxy causal learning with hidden confounders. arxiv.org/abs/2503.08371 Bozkurt, Deaner, @dimitrimeunier.bsky.social, Xu

Announcing : The 2nd International Summer School on Mathematical Aspects of Data Science mathsdata2025.github.io EPFL, Sept 1–5, 2025 Speakers: Bach @bachfrancis.bsky.social Bandeira Mallat Montanari Peyré @gabrielpeyre.bsky.social For PhD students & early-career researchers Apply before May 15!

Optimality and Adaptivity of Deep Neural Features for Instrumental Variable Regression #ICLR25 openreview.net/forum?id=ReI... NNs ✨better than fixed-feature (kernel, sieve) when target has low spatial homogeneity, ✨more sample-efficient wrt Stage 1 Kim, @dimitrimeunier.bsky.social, Suzuki, Li

Deep MMD Gradient Flow Without Adversarial Training at #ICLR2025 openreview.net/forum?id=Pf8... Do you have a GAN critic? Then you have a diffusion! Adaptive MMD gradient flow trained on a forward diffusion, competitive performance on image generation! Galashov, @vdebortoli.bsky.social

Looking forward to this!

Our joint paper with Geoffrey Wolfer @gwolfer.bsky.social "Variance-Aware Estimation of the Kernel Mean Embedding" accepted for publication in the Journal of Machine Learning Research 🥳 arxiv.org/abs/2210.06672

Congratulations @lestermackey.bsky.social !!

Hey ELLIS PhD students, need to travel but low on funds? Learn how ELSA can help with that: bit.ly/4kqjyel #ELLISPhD #MobilityFund #SustainableAI #ProjectsBuildingOnELLIS

I already advertised for this document when I posted it on arXiv, and later when it was published. This week, with the agreement of the publisher, I uploaded the published version on arXiv. Less typos, more references and additional sections including PAC-Bayes Bernstein. arxiv.org/abs/2110.11216

The slides of my talk at OIST are online: pierrealquier.github.io/slides/okina... Thanks to the organisers, and thanks to Frank Nielsen for the photo of my talk 🙏 Link to the paper: arxiv.org/abs/2412.18539

Video now public from the talk "Learning to act in noisy contexts using deep proxy learning" at the NeurIPS'24 Workshop on Causal Representation Learning! Video: neurips.cc/virtual/2024... Slides: www.gatsby.ucl.ac.uk/~gretton/cou...

super happy about this preprint! we can *finally* perform efficient exploration and find near-optimal stationary policies in infinite-horizon linear MDPs, and even use it for imitation learning :) working with @neu-rips.bsky.social and @lviano.bsky.social on this was so much fun!!

With Jack Mayo we are organizing a symposium on theory of bandit algorithms on March 10 at the University of Amsterdam. Talks by Jack Mayo, Wouter Koolen, Julia Olkhovskaya, Dirk van der Hoeven and, tentatively, Tor Lattimore. www.timvanerven.nl/events/bandi... has details and (free) registration

Better diffusions with scoring rules! Fewer, larger denoising steps using distributional losses; learn the posterior distribution of clean samples given the noisy versions. arxiv.org/pdf/2502.02483 @vdebortoli.bsky.social Galashov Guntupalli Zhou @sirbayes.bsky.social @arnauddoucet.bsky.social

Last week, the MFO Oberwolfach workshop on Overparametrization, Regularization, Identifiability & Uncertainty in ML united 48 researchers for 29 talks & plenaries. Organized by two ELLIS Programs, it advanced discussions in theoretical ML. Get details: ellis.eu/news/ellis-p...

Sad after #AISTATS2025 and #ICLR2025 notifications? As we say in Italy, when a door closes, a bigger one opens ;) If you have a fantastic paper on #uncertainty #AI #ML #causality #statML #probabilisticmodels #reasoning #impreciseprobabilities etc, consider submitting to #UAI2025 🇧🇷 deadline 10 Feb 💥

Financial Assistance applications are now open! If you face financial barriers to attending ICLR 2025, we encourage you to apply. The program offers prepay and reimbursement options. Applications are due March 2nd with decisions announced March 9th. iclr.cc/Conferences/...

Speculative sampling accelerates inference in LLMs by drafting future tokens which are verified in parallel. With @vdebortoli.bsky.social , A. Galashov & @arthurgretton.bsky.social , we extend this approach to (continuous-space) diffusion models: arxiv.org/abs/2501.05370

📢 ICML Call for Papers is out The CfP is live here: icml.cc/Conferences/..., and we also just released a blog post summarizing major updates this year: medium.com/@icml2025pc/...

ALT 2025: list of accepted papers. Congratulations to the authors ! openreview.net/group?id=alg...

The slides of my NeurIPS lecture "From Diffusion Models to Schrödinger Bridges - Generative Modeling meets Optimal Transport" can be found here drive.google.com/file/d/1eLa3...

"Learning to Act in Noisy Contexts Using Deep Proxy Learning" Talk at the #NeurIPS2024 Causal Representation Learning Workshop neurips.cc/virtual/2024... Sunday 15th December (tomorrow!), 8:45am, East Exhibition Hall C

How can you 0-shot transfer predictions of long-term performance across reward functions *and* risk-sensitive utilities? We can do this via Distributional Successor Features. Our recent work introduces the 1st tractable & provably convergent algos for learning DSFs. #NeurIPS2024 #6704 12 Dec, 11-2

Data balancing for fairness: when does it work? When does it not? "Mind the Graph When Balancing Data for Fairness or Robustness" #NeurIPS2024 West Ballroom A-D #5507 Fri 13 Dec 11 a.m. PST — 2 p.m. PST neurips.cc/virtual/2024...

Distributional SFs: enable 0-shot generalization of return *distribution* functions across a finite-dimensional reward function class "Foundations of Multivariate Distributional Reinforcement Learning" #NeurIPS2024 #6704 12 Dec 11am-2pm neurips.cc/virtual/2024... Wiltzer Farebrother Rowland

Conditional mean embeddings without Tikhonov: no saturation effect! "Optimal Rates for Vector-Valued Spectral Regularization Learning Algorithms" #NeurIPS2024 Poster #5709 12 Dec 11 a.m.— 2 p.m neurips.cc/virtual/2024... Meunier, Shen, Mollenhauer, Li

Use contrastive divergence to learn energy-based models as well as with maximum likelihood! "Near-Optimality of Contrastive Divergence Algorithms" Pierre Glaser, Kevin Han Huang at #NeurIPS2024 West Ballroom A-D #5609 Wed 11 Dec 4:30 — 7:30 p.m. PST neurips.cc/virtual/2024...

Join us this Friday, 6th of December at noon, for Xidong Feng's (Google DeepMind) talk titled "Language Model from the view of Reinforcement Learning". Happening in-person and on zoom. More details and zoom link here: ucl-ellis.github.io/dm_csml_semi...

Join us this Friday, 29th of November at noon, in person or on zoom to hear Takanori Maehara from Roku Inc talk about the Expressive Power of Graph Neural Networks. More details and zoom link here: ucl-ellis.github.io/dm_csml_semi...

It was our pleasure to host Jeremias Knoblauch at the Seminar kindly sponsored by Jump Trading. In case you missed it, the recording of his talk on Post-Bayesian Machine Learning is available here: youtu.be/0kyI3UfD1Uw

A fun interview with Charles Riou of ML New Papers, recorded at #MLSS2024 #MLSS2024Okinawa ! youtu.be/wbVoH9QUm80