A Fully Parameter-Free Second-Order Algorithm for Convex-Concave Minimax Problems with Optimal Iteration Complexity

• URL: http://arxiv.org/abs/2407.03571v1
• Date: Thu, 4 Jul 2024 01:46:07 GMT
• Title: A Fully Parameter-Free Second-Order Algorithm for Convex-Concave Minimax Problems with Optimal Iteration Complexity
• Authors: Junlin Wang, Junnan Yang, Zi Xu,
• Abstract summary: We propose a Lipschitz-free cubic regularization (LF-CR) algorithm for solving the convex-concave minimax optimization problem. We also propose a fully parameter-free cubic regularization (FF-CR) algorithm that does not require any parameters of the problem. To the best of our knowledge, the proposed FF-CR algorithm is the first completely parameter-free second-order algorithm for solving convex-concave minimax optimization problems.
• Score: 2.815239177328595
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we study second-order algorithms for the convex-concave minimax problem, which has attracted much attention in many fields such as machine learning in recent years. We propose a Lipschitz-free cubic regularization (LF-CR) algorithm for solving the convex-concave minimax optimization problem without knowing the Lipschitz constant. It can be shown that the iteration complexity of the LF-CR algorithm to obtain an $\epsilon$-optimal solution with respect to the restricted primal-dual gap is upper bounded by $\mathcal{O}(\frac{\rho\|z^0-z^*\|^3}{\epsilon})^{\frac{2}{3}}$, where $z^0=(x^0,y^0)$ is a pair of initial points, $z^*=(x^*,y^*)$ is a pair of optimal solutions, and $\rho$ is the Lipschitz constant. We further propose a fully parameter-free cubic regularization (FF-CR) algorithm that does not require any parameters of the problem, including the Lipschitz constant and the upper bound of the distance from the initial point to the optimal solution. We also prove that the iteration complexity of the FF-CR algorithm to obtain an $\epsilon$-optimal solution with respect to the gradient norm is upper bounded by $\mathcal{O}(\frac{\rho\|z^0-z^*\|^2}{\epsilon})^{\frac{2}{3}}$. Numerical experiments show the efficiency of both algorithms. To the best of our knowledge, the proposed FF-CR algorithm is the first completely parameter-free second-order algorithm for solving convex-concave minimax optimization problems, and its iteration complexity is consistent with the optimal iteration complexity lower bound of existing second-order algorithms with parameters for solving convex-concave minimax problems.

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)
• On Linear Convergence in Smooth Convex-Concave Bilinearly-Coupled Saddle-Point Optimization: Lower Bounds and Optimal Algorithms [17.227158587717934]
  We revisit the smooth convex-concave bilinearly-coupled saddle-point problem of the form $min_xmax_y f(x) + langle y,mathbfB xrangle - g(y)$. We develop the first lower complexity bounds and matching optimal linearly converging algorithms for this problem class.
  arXiv  Detail & Related papers  (2024-11-21T22:06:25Z)
• 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 Algorithm with Optimal Dimension-Dependence for Zero-Order Nonsmooth Nonconvex Stochastic Optimization [37.300102993926046]
  We study the complexity of producing neither smooth nor convex points of Lipschitz objectives which are possibly using only zero-order evaluations. Our analysis is based on a simple yet powerful. Goldstein-subdifferential set, which allows recent advancements in. nonsmooth non optimization.
  arXiv  Detail & Related papers  (2023-07-10T11:56:04Z)
• Deterministic Nonsmooth Nonconvex Optimization [94.01526844386977]
  We show that randomization is necessary to obtain a dimension-free dimension-free algorithm. Our algorithm yields the first deterministic dimension-free algorithm for optimizing ReLU networks.
  arXiv  Detail & Related papers  (2023-02-16T13:57:19Z)
• ReSQueing Parallel and Private Stochastic Convex Optimization [59.53297063174519]
  We introduce a new tool for BFG convex optimization (SCO): a Reweighted Query (ReSQue) estimator for the gradient of a function convolved with a (Gaussian) probability density. We develop algorithms achieving state-of-the-art complexities for SCO in parallel and private settings.
  arXiv  Detail & Related papers  (2023-01-01T18:51:29Z)
• The First Optimal Algorithm for Smooth and Strongly-Convex-Strongly-Concave Minimax Optimization [88.91190483500932]
  In this paper, we revisit the smooth and strongly-strongly-concave minimax optimization problem. Existing state-of-the-art methods do not match lower bound $Omegaleft(sqrtkappa_xkappa_ylog3 (kappa_xkappa_y)logfrac1epsilonright)$. We fix this fundamental issue by providing the first algorithm with $mathcalOleft( sqrtkappa_xkappa_ylog
  arXiv  Detail & Related papers  (2022-05-11T17:33:07Z)
• 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)
• Streaming Complexity of SVMs [110.63976030971106]
  We study the space complexity of solving the bias-regularized SVM problem in the streaming model. We show that for both problems, for dimensions of $frac1lambdaepsilon$, one can obtain streaming algorithms with spacely smaller than $frac1lambdaepsilon$.
  arXiv  Detail & Related papers  (2020-07-07T17:10:00Z)
• 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.