Zeroth-Order primal-dual Alternating Projection Gradient Algorithms for Nonconvex Minimax Problems with Coupled linear Constraints

• URL: http://arxiv.org/abs/2402.03352v1
• Date: Fri, 26 Jan 2024 11:22:13 GMT
• Title: Zeroth-Order primal-dual Alternating Projection Gradient Algorithms for Nonconvex Minimax Problems with Coupled linear Constraints
• Authors: Huiling Zhang, Zi Xu, Yuhong Dai
• Abstract summary: We propose two zero-order regular complexity algorithms for non minimax problems with linear constraints. To the best of our knowledge, they are first two zero-order algorithms with best for noncal complexity.
• Score: 3.898056433020865
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we study zeroth-order algorithms for nonconvex minimax problems with coupled linear constraints under the deterministic and stochastic settings, which have attracted wide attention in machine learning, signal processing and many other fields in recent years, e.g., adversarial attacks in resource allocation problems and network flow problems etc. We propose two single-loop algorithms, namely the zero-order primal-dual alternating projected gradient (ZO-PDAPG) algorithm and the zero-order regularized momentum primal-dual projected gradient algorithm (ZO-RMPDPG), for solving deterministic and stochastic nonconvex-(strongly) concave minimax problems with coupled linear constraints. The iteration complexity of the two proposed algorithms to obtain an $\varepsilon$-stationary point are proved to be $\mathcal{O}(\varepsilon ^{-2})$ (resp. $\mathcal{O}(\varepsilon ^{-4})$) for solving nonconvex-strongly concave (resp. nonconvex-concave) minimax problems with coupled linear constraints under deterministic settings and $\tilde{\mathcal{O}}(\varepsilon ^{-3})$ (resp. $\tilde{\mathcal{O}}(\varepsilon ^{-6.5})$) under stochastic settings respectively. To the best of our knowledge, they are the first two zeroth-order algorithms with iterative complexity guarantees for solving nonconvex-(strongly) concave minimax problems with coupled linear constraints under the deterministic and stochastic settings.

Related papers

• Gradient Norm Regularization Second-Order Algorithms for Solving Nonconvex-Strongly Concave Minimax Problems [2.3721580767877257]
  We propose an algorithm for solving non-strongly concave minimax problems. We show that the proposed algorithm achieves an $mathcal. stilon. $second-order norm is proved to be upper by. $tk. $k. $k. $k. $k. $k. $k. $k. $k. $k. $k. $k
  arXiv  Detail & Related papers  (2024-11-24T09:46:36Z)
• Obtaining Lower Query Complexities through Lightweight Zeroth-Order Proximal Gradient Algorithms [65.42376001308064]
  We propose two variance reduced ZO estimators for complex gradient problems. We improve the state-of-the-art function complexities from $mathcalOleft(minfracdn1/2epsilon2, fracdepsilon3right)$ to $tildecalOleft(fracdepsilon2right)$.
  arXiv  Detail & Related papers  (2024-10-03T15:04:01Z)
• An accelerated first-order regularized momentum descent ascent algorithm for stochastic nonconvex-concave minimax problems [0.4910937238451484]
  We have an accelerated regularized momentum descent ascent algorithm (FORMDA) for solving non-concave mini problems. The best complexity for bound algorithms to solve non-concave minimax problems under the station of objectivearity function.
  arXiv  Detail & Related papers  (2023-10-24T01:45:11Z)
• Decentralized Riemannian Algorithm for Nonconvex Minimax Problems [82.50374560598493]
  The minimax algorithms for neural networks have been developed to solve many problems. In this paper, we propose two types of minimax algorithms. For the setting, we propose DRSGDA and prove that our method achieves a gradient.
  arXiv  Detail & Related papers  (2023-02-08T01:42:45Z)
• A Newton-CG based barrier-augmented Lagrangian method for general nonconvex conic optimization [53.044526424637866]
  In this paper we consider finding an approximate second-order stationary point (SOSP) that minimizes a twice different subject general non conic optimization. In particular, we propose a Newton-CG based-augmentedconjugate method for finding an approximate SOSP.
  arXiv  Detail & Related papers  (2023-01-10T20:43:29Z)
• Primal Dual Alternating Proximal Gradient Algorithms for Nonsmooth Nonconvex Minimax Problems with Coupled Linear Constraints [4.70696854954921]
  Non proximal minimax problems have attracted wide attention in machine learning, signal processing many other fields in recent years. We propose DAP algorithm for solving nonsmooth non-strongly concave minimax problems.
  arXiv  Detail & Related papers  (2022-12-09T05:32:30Z)
• Best Policy Identification in Linear MDPs [70.57916977441262]
  We investigate the problem of best identification in discounted linear Markov+Delta Decision in the fixed confidence setting under a generative model. The lower bound as the solution of an intricate non- optimization program can be used as the starting point to devise such algorithms.
  arXiv  Detail & Related papers  (2022-08-11T04:12:50Z)
• Derivative-free Alternating Projection Algorithms for General Nonconvex-Concave Minimax Problems [9.173866646584031]
  In this paper, we propose an algorithm for nonsmooth zeroth-order minimax problems. We show that it can be used to attack nonconcave minimax problems.
  arXiv  Detail & Related papers  (2021-08-01T15:23:49Z)
• Gradient Free Minimax Optimization: Variance Reduction and Faster Convergence [120.9336529957224]
  In this paper, we denote the non-strongly setting on the magnitude of a gradient-free minimax optimization problem. We show that a novel zeroth-order variance reduced descent algorithm achieves the best known query complexity.
  arXiv  Detail & Related papers  (2020-06-16T17:55:46Z)
• A Unified Single-loop Alternating Gradient Projection Algorithm for Nonconvex-Concave and Convex-Nonconcave Minimax Problems [8.797831153231664]
  We develop an efficient algorithm for solving minimax problems with theoretical general convexnon objective guarantees. We show that the proposed algorithm can be used to solve both noncaveepsilon concave (strongly) and (strongly) convexnonconcave minimax problems.
  arXiv  Detail & Related papers  (2020-06-03T04:00:52Z)
• Second-order Conditional Gradient Sliding [79.66739383117232]
  We present the emphSecond-Order Conditional Gradient Sliding (SOCGS) algorithm. The SOCGS algorithm converges quadratically in primal gap after a finite number of linearly convergent iterations. It is useful when the feasible region can only be accessed efficiently through a linear optimization oracle.
  arXiv  Detail & Related papers  (2020-02-20T17:52:18Z)

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.