Salvato in:
Dettagli Bibliografici
Autori principali: Giang-Tran, Khanh-Hung, Shafiee, Soroosh, Ho-Nguyen, Nam
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2603.29870
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914436624678912
author Giang-Tran, Khanh-Hung
Shafiee, Soroosh
Ho-Nguyen, Nam
author_facet Giang-Tran, Khanh-Hung
Shafiee, Soroosh
Ho-Nguyen, Nam
contents This paper addresses constrained smooth saddle-point problems in settings where projection onto the feasible sets is computationally expensive. We bridge the gap between projection-based and projection-free optimization by introducing a unified dual dynamic smoothing framework that enables the design of efficient single-loop algorithms. Within this framework, we establish convergence results for nonconvex-concave and nonconvex-strongly concave settings. Furthermore, we show that this framework is naturally applicable to convex-concave problems. We propose and analyze three algorithmic variants based on the application of a linear minimization oracle over the minimization variable, the maximization variable, or both. Notably, our analysis yields anytime convergence guarantees without requiring a pre-specified iteration horizon. These results significantly narrow the performance gap between projection-free and projection-based methods for minimax optimization.
format Preprint
id arxiv_https___arxiv_org_abs_2603_29870
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Projection-Free Algorithms for Minimax Problems
Giang-Tran, Khanh-Hung
Shafiee, Soroosh
Ho-Nguyen, Nam
Optimization and Control
This paper addresses constrained smooth saddle-point problems in settings where projection onto the feasible sets is computationally expensive. We bridge the gap between projection-based and projection-free optimization by introducing a unified dual dynamic smoothing framework that enables the design of efficient single-loop algorithms. Within this framework, we establish convergence results for nonconvex-concave and nonconvex-strongly concave settings. Furthermore, we show that this framework is naturally applicable to convex-concave problems. We propose and analyze three algorithmic variants based on the application of a linear minimization oracle over the minimization variable, the maximization variable, or both. Notably, our analysis yields anytime convergence guarantees without requiring a pre-specified iteration horizon. These results significantly narrow the performance gap between projection-free and projection-based methods for minimax optimization.
title Projection-Free Algorithms for Minimax Problems
topic Optimization and Control
url https://arxiv.org/abs/2603.29870