3 papers
math.OC2026
Bregman meets Lévy: Stochastic mirror descent with heavy-tailed noise in continuous and discrete time
Pierre-Louis Cauvin, Panayotis Mertikopoulos
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-varian…
cs.GT2025
The impact of uncertainty on regularized learning in games
Pierre-Louis Cauvin, Davide Legacci, Panayotis Mertikopoulos
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-le…
math.PR2022
Edgeworth expansion for Bernoulli weighted mean
Pierre-Louis Cauvin
In this work, we derive an Edgeworth expansion for the Bernoulli weighted mean in the case where are i.i.d…