works on

From the 1 of 54 papers with an AI index.

most citedHumanity's Last Exam

18 citations

Showing stat.MLShow all

5 papers · 1 filter

stat.ML2026

Phase Transition for Stochastic Block Model with more than Communities

Alexandra Carpentier, Christophe Giraud, Nicolas Verzelen

Predictions from statistical physics postulate that recovery of the communities in the Stochastic Block Model (SBM) with a fixed number of communities is possible in polynomial…

stat.ML20261 cited

Conformal Prediction for Hierarchical Data

Guillaume Principato, Gilles Stoltz, Yvenn Amara-Ouali +3

We consider conformal prediction for multivariate data and focus on hierarchical data, where some components are linear combinations of others. Intuitively, the hierarchical struct…

stat.ML2026

Proximal Point Nash Learning from Human Feedback

Daniil Tiapkin, Daniele Calandriello, Denis Belomestny +5

Traditional Reinforcement Learning from Human Feedback (RLHF) often relies on reward models, frequently assuming preference structures like the Bradley--Terry model, which may not…

stat.ML2026

Optimal Stopping in Latent Diffusion Models

Yu-Han Wu, Quentin Berthet, Gérard Biau +3

We identify and analyze a surprising phenomenon of Latent Diffusion Models (LDMs) where the final steps of the diffusion can degrade sample quality. In contrast to conventional arg…

stat.ML2026

Low-degree lower bounds via almost orthonormal bases

Alexandra Carpentier, Simone Maria Giancola, Christophe Giraud +1

Low-degree polynomials have emerged as a powerful paradigm for providing evidence of statistical-computational gaps across a variety of high-dimensional statistical models [Wein25]…