Skip to content
Preprint

First-order Methods for Variational Inequality Problems with Semi-Infinite Constraints

Oct 2026 · 0 citations · 25 references
Mathematics

TL;DR

A single-loop primal-dual constraint extrapolation method (PD-ConEx) that updates primal variables, Lagrange multipliers, and worst-case constraint indices using first-order information, linearization, extrapolation, and projections only onto simple sets is proposed.

Abstract

This paper studies first-order methods for monotone variational inequalities with semi-infinite constraints and presents this model as a framework covering constrained saddle-point problems, robust optimization, distributionally robust function-constrained optimization, and generalized Nash equilibrium formulations. Since feasibility must hold over infinitely many indexed constraints, direct projection onto the full feasible region is generally difficult. Therefore, we propose a single-loop primal-dual constraint extrapolation method (PD-ConEx) that updates primal variables, Lagrange multipliers, and worst-case constraint indices using first-order information, linearization, extrapolation, and projections only onto simple sets. We establish convergence guarantees for smooth and nonsmooth regimes, showing how the achievable rates depend on strong monotonicity and strong concavity of the index block. For coupled convex-concave saddle-point problems, strong convexity in the minimization block can accelerate its smooth terms even without strong concavity in the maximization block. We also develop an adaptive smooth variant with $O(1/K)$ VI-gap and feasibility guarantees without an a priori bound on generated multipliers. Moment-based and Wasserstein distributionally robust models fit within the framework, and numerical experiments on robust quadratic instances and distributionally robust learning illustrate the method's optimality and feasibility behavior.

View source

Similar papers

Preprint Sep 2026

Primal Methods for Constrained Variational Inequalities: Optimal Rates, Feasibility Trade-offs, and Lower Bounds

Since Zhang et al. \cite{Zhang2025} introduced the first purely primal methods for monotone variational inequalities subject to convex functional constraints, the field has lacked a complete understanding of the complexity limits of this oracle class. We develop a theory that resolves the critical gaps left by their pi...

Yong-Hong Yao, L. Jolaoso, Y. Shehu et al. · 0 citations
Preprint Sep 2026

Projection-Free Algorithms for Nonsmooth Stochastic Convex-Concave Saddle-Point Problems

We study nonsmooth convex-concave saddle-point problems over compact convex sets, assuming access to stochastic subgradients of the payoff function. We develop single-loop projection-free algorithms that use linear minimization oracles over the primal and dual domains. Unlike prior projection-free approaches that rely...

Khanh-Hung Giang-Tran, Soroosh Shafiee · 0 citations
Preprint Sep 2026

Interior-point proximal methods for nonsmooth optimization in Hilbert spaces with cone-ordered constraints

We study an inexact interior-point method for nonsmooth, possibly nonconvex optimization in a Hilbert space with inequality constraints ordered by a cone in a Banach lattice, with particular emphasis on infinite-dimensional state-constrained optimal control. The objective function is given by the sum of a smooth, possi...

Behzad Azmi, Alberto De Marchi · 0 citations
Preprint Sep 2026

Stochastic Augmented Lagrangian Framework with Second-Order Convergence Guarantees for Nonconvex Expectation-Constrained Optimization

In this paper, we propose and analyze an augmented Lagrangian framework for solving stochastic nonconvex optimization problems with expectation-based equality constraints over a closed and convex constraint set. The framework generates a sequence of nonconvex primal subproblems, which are solved inexactly using stochas...

Raghu Bollapragada, Yash Kumar · 0 citations
Preprint Oct 2026

Continuous-time analysis and algorithms for linear and convex quadratic programs via exactly solvable differential inclusions

The general case for monotone differential inclusions is solved exactly, using the minimal selection principle for monotone differential inclusions, and the trajectory of the gradient flow consists of finitely many pieces, each obtained from one nonnegative least-squares problem.

G. P. Langlois, Akwum Onwunta, Jérôme Darbon · 0 citations
Preprint Sep 2026

Fast Rates and Strong Convergence of Tikhonov-Regularized Mixed-Order Primal-Dual Dynamics for Linearly Constrained Optimization Without Eventual Ball Conditions

The strong convergence of the primal trajectory is proved and fast convergence rates under the same parameter assumptions are derived under the same parameter assumptions, without imposing any eventual inside/outside-ball condition.

Hong-Lu Li, Yi-Bin Xiao · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.