425 citations
- É. Moulines17 · h 69
- Hoi-To Wai9 · h 28
- Charles Bertucci2 profiles8 · h 12
- S. M'el'eard2 profiles8 · h 13
- Aymeric Dieuleveut2 profiles7 · h 22
- Beniamin Bogosel2 profiles7 · h 14
- G. Millot2 profiles6 · h 49
- J. Garnier6 · h 43
- Josselin Garnier6
- Rémi Flamary2 profiles6 · h 33
- R. Novikov2 profiles6 · h 25
- S. Gaubert6 · h 47
- École PolytechniqueFR273 papers
- Centre National de la Recherche ScientifiqueFR63 papers
- Laboratoire de Probabilités et Modèles AléatoiresFR16 papers
- Laboratoire de Mathématiques Blaise PascalFR14 papers
- Centre de Recherche en Mathématiques de la DécisionFR13 papers
- Institut national de recherche en sciences et technologies du numériqueFR12 papers
- Université Paris NanterreFR12 papers
- Université Paris-SaclayFR12 papers
- Institut Universitaire de FranceFR10 papers
- Laboratoire Analyse et Modélisation pour la Biologie et l'EnvironnementFR10 papers
- Laboratoire de Probabilités, Statistique et ModélisationFR10 papers
- Centre Inria de SaclayFR9 papers
16 papers · 1 filter
Differentiable Expectation-Maximisation and Applications to Gaussian Mixture Model Optimal Transport
Samuel Boïté, Eloi Tanguy, Julie Delon +2
The Expectation-Maximisation (EM) algorithm is a central tool in statistics and machine learning, widely used for latent-variable models such as Gaussian Mixture Models (GMMs). Des…
Federated Majorize-Minimization: Beyond Parameter Aggregation
Aymeric Dieuleveut, Gersende Fort, Mahmoud Hegazy +1
This paper proposes a unified approach for designing stochastic optimization algorithms that robustly scale to the federated learning setting. Our work studies a class of Majorize-…
Adaptive Destruction Processes for Diffusion Samplers
Timofei Gritsaev, Nikita Morozov, Kirill Tamogashev +5
This paper explores the challenges and benefits of a trainable destruction process in diffusion samplers -- diffusion-based generative models trained to sample an unnormalised dens…
Multi-Source and Test-Time Domain Adaptation on Multivariate Signals using Spatio-Temporal Monge Alignment
Théo Gnassounou, Antoine Collas, Rémi Flamary +2
Machine learning applications on signals such as computer vision or biomedical data often face significant challenges due to the variability that exists across hardware devices or…
Improving GFlowNets with Monte Carlo Tree Search
Nikita Morozov, Daniil Tiapkin, Sergey Samsonov +2
Generative Flow Networks (GFlowNets) treat sampling from distributions over compositional discrete spaces as a sequential decision-making problem, training a stochastic policy to c…
Compression with Exact Error Distribution for Federated Learning
Mahmoud Hegazy, Rémi Leluc, Cheuk Ting Li +1
Compression schemes have been extensively used in Federated Learning (FL) to reduce the communication cost of distributed learning. While most approaches rely on a bounded variance…