Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Ferdinand Genans5 · h 1
- Olivier Wintenberger5 · h 19
- Sylvain Le Corff4 · h 4
- Stanislas Strasman2 profiles3 · h 2
- Antoine Godichon-Baggioni2 · h 2
- Antonio Ocello2 · h 3
- Claire Boyer2 profiles2 · h 6
- François-Xavier Vialard2 · h 25
- Jordan Serres2 · h 3
- Pierre Gaillard2 profiles2 · h 4
- Vincent Lemaire2 · h 2
- Alexandre Delplanque1 · h 1
- Laboratoire de Probabilités et Modèles AléatoiresFR9 papers
- Laboratoire de Probabilités, Statistique et ModélisationFR9 papers
- Sorbonne UniversitéFR9 papers
- Centre de Mathématiques Appliquées de l'École polytechniqueFR2 papers
- École PolytechniqueFR2 papers
- Institut Universitaire de FranceFR2 papers
- Laboratoire de Mathématiques d'OrsayFR2 papers
- Laboratoire d'Informatique Gaspard-MongeFR2 papers
- Université Paris-SaclayFR2 papers
- Centre Inria de SaclayFR1 paper
- Centre Inria d'Université Côte d'AzurFR1 paper
- Centre National de la Recherche ScientifiqueFR1 paper
21 papers
Theoretical Guarantees for SMC-Guided Diffusion Sampling
Stanislas Strasman, Gabriel Victorino Cardoso, Sylvain Le Corff +2
Post-hoc conditioning of pretrained diffusion models can be addressed using Sequential Monte Carlo (SMC) methods. By evolving an interacting particle system, SMC-guided diffusion s…
Non-asymptotic Convergence of Stochastic Gradient Descent in Score-based Generative Models
Stanislas Strasman, Sobihan Surendran, Sylvain Le Corff
Score-based Generative Models (SGMs) have achieved impressive performance in data generation across a wide range of applications. While the statistical properties of their sampling…
Alexandrov spaces with non negative curvature and displacement convexity of the entropy tensor
Jordan Serres
On a smooth Riemannian manifold, Aishwarya, Rotem and Shenfeld characterised nonnegative sectional curvature as the matrix displacement convexity of an entropy tensor, the Lagrangi…
A duration-augmented binary Markov chain for rainfall occurrence with long dry spells
Antoine Doizé, Denis Allard, Philippe Naveau +1
Simulating realistic wet and dry spells is central in weather generators and climate-impact studies. While finite-order Markov chains are standard, they often fail to reproduce per…
Increasing Missingness to Reduce Bias: Richardson-SGD with Missing Data
Ferdinand Genans, Erwan Scornet
Stochastic gradient methods are central to modern large-scale learning, but their use with incomplete covariates remains delicate since imputation schemes generally introduce syste…
High-Probability Minimax Adaptive Estimation in Besov Spaces via Online-to-Batch
Paul Liautaud, Pierre Gaillard, Olivier Wintenberger
We study nonparametric regression over Besov spaces from noisy observations under sub-exponential noise, aiming to achieve minimax-optimal guarantees on the integrated squared erro…
Fast and Large-Scale Unbalanced Optimal Transport via its Semi-Dual and Adaptive Gradient Methods
Ferdinand Genans
Unbalanced Optimal Transport (UOT) has emerged as a robust relaxation of standard Optimal Transport, particularly effective for handling outliers and mass variations. However, scal…
Geometry-Aware Optimal Transport: Fast Intrinsic Dimension and Wasserstein Distance Estimation
Ferdinand Genans, Olivier Wintenberger
Solving large scale Optimal Transport (OT) in machine learning typically relies on sampling measures to obtain a tractable discrete problem. While the discrete solver's accuracy is…
A Generalization of Caffarelli's Contraction Theorem to Nearly Spherical Manifolds
Yuxin Ge, Jordan Serres
We show that every nearly spherical manifold can be realized as the volume-preserving image of a round sphere, via the Brenier-McCann optimal transport map. This theorem extends Ca…
Decreasing Entropic Regularization Averaged Gradient for Semi-Discrete Optimal Transport
Ferdinand Genans, Antoine Godichon-Baggioni, François-Xavier Vialard +1
Adding entropic regularization to Optimal Transport (OT) problems has become a standard approach for designing efficient and scalable solvers. However, regularization introduces a…
Stochastic Optimization in Semi-Discrete Optimal Transport: Convergence Analysis and Minimax Rate
Ferdinand Genans, Antoine Godichon-Baggioni, François-Xavier Vialard +1
We investigate the semi-discrete Optimal Transport (OT) problem, where a continuous source measure is transported to a discrete target measure , with particular attention to…
Attention-based clustering
Rodrigo Maulen-Soto, Pierre Marion, Claire Boyer
Transformers have emerged as a powerful neural network architecture capable of tackling a wide range of learning tasks. In this work, we provide a theoretical analysis of their abi…
Transductive Conformal Inference for Full Ranking
Jean-Baptiste Fermanian, Pierre Humbert, Gilles Blanchard
We introduce a method based on Conformal Prediction (CP) to quantify the uncertainty of full ranking algorithms. We focus on a specific scenario where items are to be ranked…
A randomisation method for mean-field control problems with common noise
Robert Denkert, Idris Kharroubi, Huyên Pham
We study mean-field control (MFC) problems with common noise using the control randomisation framework, where we substitute the control process with an independent Poisson point pr…
The Deep Latent Position Block Model For The Block Clustering And Latent Representation Of Networks
Rémi Boutin, Pierre Latouche, Charles Bouveyron
The increased quantity of data has led to a soaring use of networks to model relationships between different objects, represented as nodes. Since the number of nodes can be particu…
Hyperbolic absolutely continuous invariant measures for C^r one-dimensional maps
Alexandre Delplanque
For r > 1, we show, using the Ledrappier-Young entropy characterization of SRB measures for non-invertible maps, that if a C^r map f of the interval or the circle has its Lyapunov…
Change-point detection in regression models for ordered data via the max-EM algorithm
Modibo Diabaté, Grégory Nuel, Olivier Bouaziz
We consider the problem of breakpoint detection in a regression modeling framework. To that end, we introduce a novel method, the max-EM algorithm which combines a constrained Hidd…
An analysis of the noise schedule for score-based generative models
Stanislas Strasman, Antonio Ocello, Claire Boyer +2
Score-based generative models (SGMs) aim at estimating a target data distribution by learning score functions using only noise-perturbed samples from the target.Recent literature h…
Variational excess risk bound for general state space models
Élisabeth Gassiat, Sylvain Le Corff
In this paper, we consider variational autoencoders (VAE) for general state space models. We consider a backward factorization of the variational distributions to analyze the exces…
Boundary correlations for the Z-invariant Ising Model
Tristan Pham-Mariotti
Consider the natural graph associated to a rhombus tiling of a polygonal regionin the plane. The spin correlations between boundary vertices of this graph inthe Z-invariant Ising m…
Reimagining Demand-Side Management with Mean Field Learning
Bianca Marin Moreno, Margaux Brégère, Pierre Gaillard +1
Integrating renewable energy into the power grid while balancing supply and demand is a complex issue, given its intermittent nature. Demand side management (DSM) offers solutions…