Diffusion Optimistic Learning for Min-Max Optimization

H. Cai; Sulaiman A. Alghunaim; Ali H. Sayed

ICASSP 2024accepted0 citations

Diffusion Optimistic Learning for Min-Max Optimization

H. Cai, Sulaiman A. Alghunaim, Ali H. Sayed

Abstract

This work introduces and studies the convergence of a stochastic diffusion-optimistic learning (DOL) strategy for solving distributed nonconvex (NC) and Polyak–Lojasiewicz (PL) min-max optimization problems. Problems of this type are of interest due to a wide range of applications, including in generative adversarial networks (GANs), adversarial machine learning, and reinforcement learning. We prove that the DOL algorithm approaches an ε-stationary point through cooperation among agents following a left-stochastic communication protocol. The good performance of the proposed algorithm is illustrated by means of computer simulations.

BibTeX

@inproceedings{icassp2024_diffusionoptimis,
  title = {Diffusion Optimistic Learning for Min-Max Optimization},
  author = {H. Cai and Sulaiman A. Alghunaim and Ali H. Sayed},
  booktitle = {ICASSP 2024},
  year = {2024}
}