A Primal-Dual Approach to Solving Variational Inequalities with General Constraints

• URL: http://arxiv.org/abs/2210.15659v4
• Date: Sat, 3 Aug 2024 17:54:40 GMT
• Title: A Primal-Dual Approach to Solving Variational Inequalities with General Constraints
• Authors: Tatjana Chavdarova, Tong Yang, Matteo Pagliardini, Michael I. Jordan,
• Abstract summary: Yang et al. (2023) recently showed how to use first-order gradient methods to solve general variational inequalities. We prove the convergence of this method and show that the gap function of the last iterate of the method decreases at a rate of $O(frac1sqrtK)$ when the operator is $L$-Lipschitz and monotone.
• Score: 54.62996442406718
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Yang et al. (2023) recently showed how to use first-order gradient methods to solve general variational inequalities (VIs) under a limiting assumption that analytic solutions of specific subproblems are available. In this paper, we circumvent this assumption via a warm-starting technique where we solve subproblems approximately and initialize variables with the approximate solution found at the previous iteration. We prove the convergence of this method and show that the gap function of the last iterate of the method decreases at a rate of $O(\frac{1}{\sqrt{K}})$ when the operator is $L$-Lipschitz and monotone. In numerical experiments, we show that this technique can converge much faster than its exact counterpart. Furthermore, for the cases when the inequality constraints are simple, we introduce an alternative variant of ACVI and establish its convergence under the same conditions. Finally, we relax the smoothness assumptions in Yang et al., yielding, to our knowledge, the first convergence result for VIs with general constraints that does not rely on the assumption that the operator is $L$-Lipschitz.

Related papers

• The inexact power augmented Lagrangian method for constrained nonconvex optimization [44.516958213972885]
  This work introduces an unconventional augmented Lagrangian term, where the augmenting term is a Euclidean norm raised to a power. We show that using lower powers for augmenting term to faster rate, albeit with a slower decrease in residual. Our results further show that using lower powers for augmenting term to faster rate, albeit with a slower decrease in residual.
  arXiv  Detail & Related papers  (2024-10-26T11:31:56Z)
• Some Primal-Dual Theory for Subgradient Methods for Strongly Convex Optimization [0.0]
  We consider subgradient methods for strongly convex but potentially nonsmooth non-Lipschitz optimization. We provide new equivalent dual descriptions for the classic subgradient method, the proximal subgradient method, and the switching subgradient method.
  arXiv  Detail & Related papers  (2023-05-27T01:56:09Z)
• High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded Variance [59.211456992422136]
  We propose algorithms with high-probability convergence results under less restrictive assumptions. These results justify the usage of the considered methods for solving problems that do not fit standard functional classes in optimization.
  arXiv  Detail & Related papers  (2023-02-02T10:37:23Z)
• Solving Constrained Variational Inequalities via an Interior Point Method [88.39091990656107]
  We develop an interior-point approach to solve constrained variational inequality (cVI) problems. We provide convergence guarantees for ACVI in two general classes of problems. Unlike previous work in this setting, ACVI provides a means to solve cVIs when the constraints are nontrivial.
  arXiv  Detail & Related papers  (2022-06-21T17:55:13Z)
• Tight Last-Iterate Convergence of the Extragradient Method for Constrained Monotone Variational Inequalities [4.6193503399184275]
  We show the last-iterate convergence rate of the extragradient method for monotone and Lipschitz variational inequalities with constraints. We develop a new approach that combines the power of the sum-of-squares programming with the low dimensionality of the update rule of the extragradient method.
  arXiv  Detail & Related papers  (2022-04-20T05:12:11Z)
• Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis under Expected Co-coercivity [49.66890309455787]
  We introduce the expected co-coercivity condition, explain its benefits, and provide the first last-iterate convergence guarantees of SGDA and SCO. We prove linear convergence of both methods to a neighborhood of the solution when they use constant step-size. Our convergence guarantees hold under the arbitrary sampling paradigm, and we give insights into the complexity of minibatching.
  arXiv  Detail & Related papers  (2021-06-30T18:32:46Z)
• Simple and optimal methods for stochastic variational inequalities, I: operator extrapolation [9.359939442911127]
  We first present a novel operator extrapolation (OE) method for solving deterministic variational inequality (VI) problems. We then introduce the operator extrapolation (SOE) method and establish its optimal convergence behavior for solving different inequality VI problems.
  arXiv  Detail & Related papers  (2020-11-05T17:20:19Z)
• Approximation Schemes for ReLU Regression [80.33702497406632]
  We consider the fundamental problem of ReLU regression. The goal is to output the best fitting ReLU with respect to square loss given to draws from some unknown distribution.
  arXiv  Detail & Related papers  (2020-05-26T16:26:17Z)
• Gradient-Free Methods for Saddle-Point Problem [125.99533416395765]
  We generalize the approach Gasnikov et. al., 2017, which allows to solve (stochastic) convex optimization problems with an inexact gradient-free oracle. Our approach reduces $fracnlog n$ times the required number of oracle calls. In the second part of the paper, we analyze the case when such an assumption cannot be made, we propose a general approach on how to modernize the method to solve this problem.
  arXiv  Detail & Related papers  (2020-05-12T16:44:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.