activity
20242026
collaborators

8 papers

cs.LG2026

Local exponential stability of mean-field Langevin descent-ascent and associated particle system

Geuntaek Seo, Minseop Shin, Pierre Monmarché +1

We study the mean-field Langevin descent-ascent (MFL-DA), a coupled optimization dynamics on the space of probability measures for entropically regularized two-player zero-sum game…

math.PR2025

Piecewise deterministic sampling with splitting schemes

Andrea Bertazzi, Paul Dobson, Pierre Monmarché

We introduce Markov chain Monte Carlo (MCMC) algorithms based on numerical approximations of piecewise-deterministic Markov processes obtained with the framework of splitting schem…

math.PR2025

Free energy Wasserstein gradient flow and their particle counterparts: toy model, (degenerate) PL inequalities and exit times

Pierre Monmarché

In finite dimension, the long-time and metastable behavior of a gradient flow perturbated by a small Brownian noise is well understood. A similar situation arises when a Wasserstei…

math.PR2025

Exponential Ergodicity in Relative Entropy and -Wasserstein Distance for non-equilibrium partially dissipative Kinetic SDEs

Xing Huang, Eva Kopfer, Pierre Monmarché +1

In this paper, we derive exponential ergodicity in relative entropy for general kinetic SDEs under a partially dissipative condition. It covers non-equilibrium situations where the…

math.AP2025

Local convergence rates for Wasserstein gradient flows and McKean-Vlasov equations with multiple stationary solutions

Pierre Monmarché, Julien Reygner

Non-linear versions of log-Sobolev inequalities, that link a free energy to its dissipation along the corresponding Wasserstein gradient flow (i.e. corresponds to Polyak-Lojasiewic…

math.OC2025

Convergence of Time-Averaged Mean Field Gradient Descent Dynamics for Continuous Multi-Player Zero-Sum Games

Yulong Lu, Pierre Monmarché

The approximation of mixed Nash equilibria (MNE) for zero-sum games with mean-field interacting players has recently raised much interest in machine learning. In this paper we prop…