Towards Sharper Risk Bounds for Minimax Problems

• URL: http://arxiv.org/abs/2410.08497v1
• Date: Fri, 11 Oct 2024 03:50:23 GMT
• Title: Towards Sharper Risk Bounds for Minimax Problems
• Authors: Bowei Zhu, Shaojie Li, Yong Liu,
• Abstract summary: Minimax problems have achieved success in machine learning such as adversarial, robust optimization, reinforcement learning. For theoretical analysis, current optimal excess risk bounds are composed by generalization error and present 1/n-rates in strongly-strongly-concave (SC-SC) We analyze some popular algorithms such as empirical saddle point (GDA), gradient descent (DA) and gradient descent (SG) We derive n times faster than results in minimax problems.
• Score: 23.380477456114118
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Minimax problems have achieved success in machine learning such as adversarial training, robust optimization, reinforcement learning. For theoretical analysis, current optimal excess risk bounds, which are composed by generalization error and optimization error, present 1/n-rates in strongly-convex-strongly-concave (SC-SC) settings. Existing studies mainly focus on minimax problems with specific algorithms for optimization error, with only a few studies on generalization performance, which limit better excess risk bounds. In this paper, we study the generalization bounds measured by the gradients of primal functions using uniform localized convergence. We obtain a sharper high probability generalization error bound for nonconvex-strongly-concave (NC-SC) stochastic minimax problems. Furthermore, we provide dimension-independent results under Polyak-Lojasiewicz condition for the outer layer. Based on our generalization error bound, we analyze some popular algorithms such as empirical saddle point (ESP), gradient descent ascent (GDA) and stochastic gradient descent ascent (SGDA). We derive better excess primal risk bounds with further reasonable assumptions, which, to the best of our knowledge, are n times faster than exist results in minimax problems.

Related papers

• Riemannian stochastic optimization methods avoid strict saddle points [68.80251170757647]
  We show that policies under study avoid strict saddle points / submanifolds with probability 1. This result provides an important sanity check as it shows that, almost always, the limit state of an algorithm can only be a local minimizer.
  arXiv  Detail & Related papers  (2023-11-04T11:12:24Z)
• Can Decentralized Stochastic Minimax Optimization Algorithms Converge Linearly for Finite-Sum Nonconvex-Nonconcave Problems? [56.62372517641597]
  Decentralized minimax optimization has been actively studied in the past few years due to its application in a wide range machine learning. This paper develops two novel decentralized minimax optimization algorithms for the non-strongly-nonconcave problem.
  arXiv  Detail & Related papers  (2023-04-24T02:19:39Z)
• What is a Good Metric to Study Generalization of Minimax Learners? [24.577243536475233]
  Minimax optimization has served as backbone of many machine learning (ML) problems. How the solution trained on data performs on metric testing has been relatively underexplored. We propose a new metric generalization minimax learners: the primal, to answer these issues.
  arXiv  Detail & Related papers  (2022-06-09T13:39:06Z)
• A general sample complexity analysis of vanilla policy gradient [101.16957584135767]
  Policy gradient (PG) is one of the most popular reinforcement learning (RL) problems. "vanilla" theoretical understanding of PG trajectory is one of the most popular methods for solving RL problems.
  arXiv  Detail & Related papers  (2021-07-23T19:38:17Z)
• Stability and Generalization of Stochastic Gradient Methods for Minimax Problems [71.60601421935844]
  Many machine learning problems can be formulated as minimax problems such as Generative Adversarial Networks (GANs) We provide a comprehensive generalization analysis of examples from training gradient methods for minimax problems.
  arXiv  Detail & Related papers  (2021-05-08T22:38:00Z)
• Towards Optimal Problem Dependent Generalization Error Bounds in Statistical Learning Theory [11.840747467007963]
  We study problem-dependent rates that scale near-optimally with the variance, the effective loss errors, or the norms evaluated at the "best gradient hypothesis" We introduce a principled framework dubbed "uniform localized convergence" We show that our framework resolves several fundamental limitations of existing uniform convergence and localization analysis approaches.
  arXiv  Detail & Related papers  (2020-11-12T04:07:29Z)
• Stochastic Hard Thresholding Algorithms for AUC Maximization [49.00683387735522]
  We develop a hard thresholding algorithm for AUC in distributiond classification. We conduct experiments to show the efficiency and effectiveness of the proposed algorithms.
  arXiv  Detail & Related papers  (2020-11-04T16:49:29Z)
• Train simultaneously, generalize better: Stability of gradient-based minimax learners [12.691047660244331]
  We show a key role in the performance of the trained minimax model under both convex concave and non-concave minimax settings. We discuss several numerical results indicating the role of optimization algorithms in the generalization of learned minimax models.
  arXiv  Detail & Related papers  (2020-10-23T17:44:43Z)
• Fast Objective & Duality Gap Convergence for Non-Convex Strongly-Concave Min-Max Problems with PL Condition [52.08417569774822]
  This paper focuses on methods for solving smooth non-concave min-max problems, which have received increasing attention due to deep learning (e.g., deep AUC)
  arXiv  Detail & Related papers  (2020-06-12T00:32:21Z)

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.