Target Mirror Descent: A Unifying Framework for Solving Monotone Variational Inequalities

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Yu-Wen, Kizilkale, Can, Arcak, Murat
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917424631119872
author Chen, Yu-Wen
Kizilkale, Can
Arcak, Murat
author_facet Chen, Yu-Wen
Kizilkale, Can
Arcak, Murat
contents It is well known that mirror descent may diverge or cycle on merely monotone variational inequalities. In this paper, we propose \emph{Target Mirror Descent} (TMD), a unified framework that stabilizes monotone flows via a target point correction mechanism in the dual update. By appropriate design choices, TMD recovers the proximal point algorithm, extragradient methods, splitting methods, Brown-von Neumann-Nash dynamics, forward-backward-forward dynamics, and discounted mirror descent as special cases. Thus, we establish a unified perspective on these landmark algorithms and their convergence. Beyond unification, we leverage the TMD framework to correct an equilibrium misalignment in discounted mirror descent and to generalize its higher-order extension beyond interior solutions. Moreover, a key structural feature of TMD is the explicit decoupling of the mirror map from the target determination, which enables \emph{geometric ensembles}: multiple algorithms solve the same problem in parallel using distinct mirror maps, while sharing a common dual update. We show that such an ensemble rigorously reduces to a single TMD with a synthesized mirror map, and thus inherits these convergence guarantees.
format Preprint
id arxiv_https___arxiv_org_abs_2604_18813
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Target Mirror Descent: A Unifying Framework for Solving Monotone Variational Inequalities
Chen, Yu-Wen
Kizilkale, Can
Arcak, Murat
Optimization and Control
Computer Science and Game Theory
It is well known that mirror descent may diverge or cycle on merely monotone variational inequalities. In this paper, we propose \emph{Target Mirror Descent} (TMD), a unified framework that stabilizes monotone flows via a target point correction mechanism in the dual update. By appropriate design choices, TMD recovers the proximal point algorithm, extragradient methods, splitting methods, Brown-von Neumann-Nash dynamics, forward-backward-forward dynamics, and discounted mirror descent as special cases. Thus, we establish a unified perspective on these landmark algorithms and their convergence. Beyond unification, we leverage the TMD framework to correct an equilibrium misalignment in discounted mirror descent and to generalize its higher-order extension beyond interior solutions. Moreover, a key structural feature of TMD is the explicit decoupling of the mirror map from the target determination, which enables \emph{geometric ensembles}: multiple algorithms solve the same problem in parallel using distinct mirror maps, while sharing a common dual update. We show that such an ensemble rigorously reduces to a single TMD with a synthesized mirror map, and thus inherits these convergence guarantees.
title Target Mirror Descent: A Unifying Framework for Solving Monotone Variational Inequalities
topic Optimization and Control
Computer Science and Game Theory
url https://arxiv.org/abs/2604.18813