PaperScope
LIVE · 2026-09-09 05:40 UTC

How to Make the Gradient Mapping Small for Constrained Stochastic Min-Max Problems and Beyond

Ahmet Alacaoglu

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.08380 v1
Category
Submitted
2026-09-08

Abstract

We study the stochastic first-order oracle complexity for constrained or regularized convex-concave min-max optimization and stochastic monotone variational inequalities. We focus on the case when suboptimality is measured in terms of the gradient mapping, also known as, forward-backward or natural residual, an optimality notion that generalizes the gradient norm for unconstrained problems. In this setting, under standard unbiased oracle access with now-standard variance assumptions, the best-known complexity for making the norm of the gradient mapping less than $\varepsilon$ is $\widetilde{O}(\varepsilon^{-4})$, compared to the near-optimal $\widetilde{O}(\varepsilon^{-2})$ that is established in the unconstrained case. We bridge this gap to improve the gradient mapping complexity for constrained convex-concave min-max problems to $\widetilde{O}(\varepsilon^{-2})$. We then extend to prove the same complexity for problems without the bounded variance, by using the Blum-Gladyshev assumption.

arXiv abs page · PDF · same-day batch