425 citations
- École PolytechniqueFR427 papers
- Centre National de la Recherche ScientifiqueFR106 papers
- Université Paris-SaclayFR25 papers
- Laboratoire de Probabilités et Modèles AléatoiresFR21 papers
- Centre de Recherche en Mathématiques de la DécisionFR20 papers
- Sorbonne UniversitéFR18 papers
- Université Paris CitéFR18 papers
- Institut national de recherche en sciences et technologies du numériqueFR17 papers
- Institut Polytechnique de ParisFR17 papers
- Laboratoire de Mathématiques Blaise PascalFR16 papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR15 papers
- École Normale Supérieure - PSLFR15 papers
6 papers · 2 filters
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…
Improving the evaluation of samplers on multi-modal targets
Louis Grenioux, Maxence Noble, Marylou Gabrié
Addressing multi-modality constitutes one of the major challenges of sampling. In this reflection paper, we advocate for a more systematic evaluation of samplers towards two source…
Personalized Convolutional Dictionary Learning of Physiological Time Series
Axel Roques, Samuel Gruffaz, Kyurae Kim +2
Human physiological signals tend to exhibit both global and local structures: the former are shared across a population, while the latter reflect inter-individual variability. For…
Scaffold with Stochastic Gradients: New Analysis with Linear Speed-Up
Paul Mangold, Alain Durmus, Aymeric Dieuleveut +1
This paper proposes a novel analysis for the Scaffold algorithm, a popular method for dealing with data heterogeneity in federated learning. While its convergence in deterministic…
Bit-Level Discrete Diffusion with Markov Probabilistic Models: An Improved Framework with Sharp Convergence Bounds under Minimal Assumptions
Le-Tuyet-Nhi Pham, Dario Shariatian, Antonio Ocello +2
This paper introduces Discrete Markov Probabilistic Models (DMPMs), a novel discrete diffusion algorithm for discrete data generation. The algorithm operates in discrete bit space,…
Beyond Log-Concavity and Score Regularity: Improved Convergence Bounds for Score-Based Generative Models in W2-distance
Marta Gentiloni-Silveri, Antonio Ocello
Score-based Generative Models (SGMs) aim to sample from a target distribution by learning score functions using samples perturbed by Gaussian noise. Existing convergence bounds for…