activity
20242026
collaborators

16 papers

math.PR2026

Quantitative contraction rates for Sinkhorn's algorithm: beyond bounded costs and compact marginals

Giovanni Conforti, Alain Durmus, Giacomo Greco

We show non-asymptotic exponential convergence of Sinkhorn iterates to the Schrödinger potentials, solutions of the quadratic Entropic Optimal Transport problem on

cs.CV2026

Efficient Zero-Shot Inpainting with Decoupled Diffusion Guidance

Badr Moufad, Navid Bagheri Shouraki, Alain Oliviero Durmus +4

Diffusion models have emerged as powerful priors for image editing tasks such as inpainting and local modification, where the objective is to generate realistic content that remain…

cs.LG2026

Online Decision-Focused Learning

Aymeric Capitaine, Maxime Haddouche, Eric Moulines +3

Decision-focused learning (DFL) is an increasingly popular paradigm for training predictive models whose outputs are used in decision-making tasks. Instead of merely optimizing for…

cs.LG2026

Categorical Reparameterization with Denoising Diffusion models

Samson Gourevitch, Alain Durmus, Eric Moulines +2

Learning models with categorical variables requires optimizing expectations over discrete distributions, a setting in which stochastic gradient-based optimization is challenging du…

stat.ML2025

Refined Analysis of Federated Averaging and Federated Richardson-Romberg

Paul Mangold, Alain Durmus, Aymeric Dieuleveut +2

In this paper, we present a novel analysis of \FedAvg with constant step size, relying on the Markov property of the underlying process. We demonstrate that the global iterates of…

cs.GT2025

Online Decision-Making in Tree-Like Multi-Agent Games with Transfers

Antoine Scheid, Etienne Boursier, Alain Durmus +2

The widespread deployment of Machine Learning systems everywhere raises challenges, such as dealing with interactions or competition between multiple learners. In that goal, we stu…