Primal Methods for Variational Inequality Problems with Functional Constraints

arXiv:2403.12859v1 Announce Type: cross
Abstract: Constrained variational inequality problems are recognized for their broad applications across various fields including machine learning and operations research. First-order methods have emerged as the standard approach for solving these problems due to their simplicity and scalability. However, they typically rely on projection or linear minimization oracles to navigate the feasible set, which becomes computationally expensive in practical scenarios featuring multiple functional constraints. Existing efforts to tackle such functional constrained variational inequality problems have centered …

abstract applications arxiv constraints cs.lg fields functional however inequality linear machine machine learning math.oc operations primal projection research scalability simplicity standard stat.ml type