EUROPT 2025
Abstract Submission

EURO-Online login

204. Minimizing the smoothed gap to solve saddle point problems

Invited abstract in session MD-1: Smoothing techniques for nonsmooth optimization, stream Nonsmooth and nonconvex optimization.

Monday, 16:30-18:30

Authors (first author is the speaker)

1. Olivier Fercoq
Telecom Paris University

Abstract

In this work, we minimize the self-centered smoothed gap, a recently introduced optimality measure, in order to solve convex-concave saddle point problems. The self-centered smoothed gap can be computed as the sum of a convex, possibly nonsmooth function and a smooth weakly convex function. Although it is not convex, we propose an algorithm that minimizes this quantity, effectively reducing convex-concave saddle point problems to a minimization problem. Its worst case complexity is comparable to the state of the art, and the algorithm enjoys linear convergence in favorable cases.

Keywords

Status: accepted


Back to the list of papers