output
20162022
most citedOptimistic mirror descent in saddle-point problems: Going the extra (gradient) mile

114 citations

researchers with a paper here

Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.

collaborating institutions
Showing 2018Show all

5 papers · 1 filter

cs.GT2018★ 28 cited

Bandit learning in concave -person games

Mario Bravo, David S. Leslie, Panayotis Mertikopoulos

This paper examines the long-run behavior of learning with bandit feedback in non-cooperative concave games. The bandit framework accounts for extremely low-information environment…

cs.GT2018★ 10 cited

Multi-agent online learning in time-varying games

Benoit Duvocelle, Panayotis Mertikopoulos, Mathias Staudigl +1

We examine the long-run behavior of multi-agent online learning in games that evolve over time. Specifically, we focus on a wide class of policies based on mirror descent, and we s…

cs.LG2018★ 114 cited

Optimistic mirror descent in saddle-point problems: Going the extra (gradient) mile

Panayotis Mertikopoulos, Bruno Lecouat, Houssam Zenati +3

Owing to their connection with generative adversarial networks (GANs), saddle-point problems have recently attracted considerable interest in machine learning and beyond. By necess…

cs.PF2018★ 4 cited

Dispatching to Parallel Servers: Solutions of Poisson's Equation for First-Policy Improvement

Olivier Bilenne

Policy iteration techniques for multiple-server dispatching rely on the computation of value functions. In this context, we consider the continuous-space M/G/1-FCFS queue endowed w…

math.PR2018★ 14 cited

Power-of--Choices with Memory: Fluid Limit and Optimality

Jonatha Anselmi, Francois Dufour

In multi-server distributed queueing systems, the access of stochastically arriving jobs to resources is often regulated by a dispatcher, also known as load balancer. A fundamental…