Nonlinear preconditioned primal-dual method for a class of structured minimax problems

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Lu, Wang, Hongxia, Zhang, Hui
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909067673337856
author Zhang, Lu
Wang, Hongxia
Zhang, Hui
author_facet Zhang, Lu
Wang, Hongxia
Zhang, Hui
contents We propose and analyze a general framework called nonlinear preconditioned primal-dual with projection for solving nonconvex-nonconcave and non-smooth saddle-point problems. The framework consists of two steps. The first is a nonlinear preconditioned map followed by a relaxed projection onto the separating hyperspace we construct. One key to the method is the selection of preconditioned operators, which tailors to the structure of the saddle-point problem and is allowed to be nonlinear and asymmetric. The other is the construction of separating hyperspace, which guarantees fast convergence. This framework paves the way for constructing nonlinear preconditioned primal-dual algorithms. We show that weak convergence, and so is sublinear convergence under the assumption of the convexity of saddle-point problems and linear convergence under a metric subregularity. We also show that many existing primal-daul methods, such as the generalized primal-dual algorithm method, are special cases of relaxed preconditioned primal-dual with projection.
format Preprint
id arxiv_https___arxiv_org_abs_2401_05143
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Nonlinear preconditioned primal-dual method for a class of structured minimax problems
Zhang, Lu
Wang, Hongxia
Zhang, Hui
Optimization and Control
Numerical Analysis
We propose and analyze a general framework called nonlinear preconditioned primal-dual with projection for solving nonconvex-nonconcave and non-smooth saddle-point problems. The framework consists of two steps. The first is a nonlinear preconditioned map followed by a relaxed projection onto the separating hyperspace we construct. One key to the method is the selection of preconditioned operators, which tailors to the structure of the saddle-point problem and is allowed to be nonlinear and asymmetric. The other is the construction of separating hyperspace, which guarantees fast convergence. This framework paves the way for constructing nonlinear preconditioned primal-dual algorithms. We show that weak convergence, and so is sublinear convergence under the assumption of the convexity of saddle-point problems and linear convergence under a metric subregularity. We also show that many existing primal-daul methods, such as the generalized primal-dual algorithm method, are special cases of relaxed preconditioned primal-dual with projection.
title Nonlinear preconditioned primal-dual method for a class of structured minimax problems
topic Optimization and Control
Numerical Analysis
url https://arxiv.org/abs/2401.05143