Pierre-Louis Cauvin — accepted AI-conference papers

2026

Bregman meets Lévy: Stochastic Mirror Descent with Heavy-Tailed Noise in Continuous and Discrete Time

Pierre-Louis Cauvin, Panayotis Mertikopoulos

ICML 2026poster

We study the robustness of stochastic mirror descent (SMD) under heavy-tailed noise, focusing on whether the method retains its convergence guarantees when run with infinite-variance stochastic gradient input. To address this question in a principled manner, we begin by introducing a continuous-time…

Cited by 0 Source ↗Scholar ↗

2025

The impact of uncertainty on regularized learning in games

Pierre-Louis Cauvin, Davide Legacci, Panayotis Mertikopoulos

ICML 2025poster

In this paper, we investigate how randomness and uncertainty influence learning in games. Specifically, we examine a perturbed variant of the dynamics of “follow-the-regularized-leader” (FTRL), where the players’ payoff observations and strategy updates are continually impacted by random shocks. Our…

Cited by 0 Source ↗PDF ↗Scholar ↗