Pith. sign in

Convergence of Extragradient SVRG for Variational Inequalities: Error Bounds and Increasing Iterate Averaging

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

We study the last-iterate convergence of variance reduction methods for extragradient (EG) algorithms for a class of variational inequalities satisfying error-bound conditions. Previously, last-iterate linear convergence was only known under strong monotonicity. We show that EG algorithms with SVRG-style variance reduction, denoted SVRG-EG, attain last-iterate linear convergence under a general error-bound condition much weaker than strong monotonicity. This condition captures a broad class of non-strongly monotone problems, such as bilinear saddle-point problems commonly encountered in two-player zero-sum Nash equilibrium computation. Next, we establish linear last-iterate convergence of SVRG-EG with an improved guarantee under the weak sharpness assumption. Furthermore, motivated by the empirical efficiency of increasing iterate averaging techniques in solving saddle-point problems, we also establish new convergence results for SVRG-EG with such techniques.

citation-role summary

method 1

citation-polarity summary

fields

math.OC 1

years

2025 1

verdicts

CONDITIONAL 1

roles

method 1

polarities

use method 1

representative citing papers

Complexity guarantees for risk-neutral generalized Nash equilibrium problems

math.OC · 2025-06-13 · conditional · novelty 6.0

A double-loop variance-reduced stochastic forward-backward-forward method computes variational equilibria in risk-neutral stochastic games, with a.s. convergence, linear rates under strong monotonicity, and O(epsilon^-3) sample complexity under monotonicity.

citing papers explorer

Showing 1 of 1 citing paper.

  • Complexity guarantees for risk-neutral generalized Nash equilibrium problems math.OC · 2025-06-13 · conditional · none · ref 33 · internal anchor

    A double-loop variance-reduced stochastic forward-backward-forward method computes variational equilibria in risk-neutral stochastic games, with a.s. convergence, linear rates under strong monotonicity, and O(epsilon^-3) sample complexity under monotonicity.