Logo image
A generalized Frank–Wolfe method with “dual averaging” for strongly convex composite optimization
Journal article   Open access   Peer reviewed

A generalized Frank–Wolfe method with “dual averaging” for strongly convex composite optimization

Renbo Zhao and Qiuyun Zhu
Optimization letters, Vol.17(7), pp.1595-1611
09/2023
DOI: 10.1007/s11590-022-01951-0
url
https://doi.org/10.1007/s11590-022-01951-0View
Published (Version of record) Open Access

Abstract

We propose a simple variant of the generalized Frank–Wolfe method for solving strongly convex composite optimization problems, by introducing an additional averaging step on the dual variables. We show that in this variant, one can choose a simple constant step-size and obtain a linear convergence rate on the duality gaps. By leveraging the convergence analysis of this variant, we then analyze the local convergence rate of the logistic fictitious play algorithm, which is well-established in game theory but lacks any form of convergence rate guarantees. We show that, with high probability, this algorithm converges locally at rate O (1/ t ), in terms of certain expected duality gap.
Computational Intelligence Mathematics Mathematics and Statistics Numerical and Computational Physics Operations Research/Decision Theory Optimization Original Paper Simulation

Details

Metrics

Logo image