From the 1 of 54 papers with an AI index.
18 citations
- 84084 Italy3 · h 4
- Himanshu Gupta3 profiles3 · h 10
- Khalid Baadi3 · h 2
- Micah Carroll2 profiles3 · h 15
- Michael Kirchhof2 profiles3 · h 10
- Orion Weller2 profiles3 · h 22
- Zheng-Xin Yong3 profiles3 · h 18
- Aaron Fenyes2 profiles2 · h 1
- Abdallah Galal2 profiles2 · h 1
- Alexandra Carpentier2 · h 4
- Alon Amit2 profiles2 · h 8
- Ankit Singh2 profiles2 · h 3
- Université Paris-SaclayFR18 papers
- Centre National de la Recherche ScientifiqueFR17 papers
- Laboratoire de Mathématiques Blaise PascalFR5 papers
- Université Paris CitéFR5 papers
- Département de mathématiques et applicationsFR4 papers
- Centre de Mathématiques Appliquées de l'École polytechniqueFR3 papers
- Delft University of TechnologyNL3 papers
- École Normale Supérieure de LyonFR3 papers
- École Normale Supérieure - PSLFR3 papers
- École PolytechniqueFR3 papers
- Google DeepMind (United Kingdom)GB3 papers
- Google (United Kingdom)GB3 papers
5 papers · 1 filter
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…
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…
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…
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…
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]…