Extragradient Method for $(L_0, L_1)$-Lipschitz Root-finding Problems

• URL: http://arxiv.org/abs/2510.22421v1
• Date: Sat, 25 Oct 2025 19:43:01 GMT
• Title: Extragradient Method for $(L_0, L_1)$-Lipschitz Root-finding Problems
• Authors: Sayantan Choudhury, Nicolas Loizou,
• Abstract summary: The extragradient method (EG) has become a cornerstone technique for solving min-max optimization, root-finding problems, and variational inequalities (VIs)<n>We propose a novel step size strategy for EG to solve root-finding problems and establish sublinear convergence rates for monotone operators and linear convergence rates for strongly monotone operators.
• Score: 15.649189456012811
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Introduced by Korpelevich in 1976, the extragradient method (EG) has become a cornerstone technique for solving min-max optimization, root-finding problems, and variational inequalities (VIs). Despite its longstanding presence and significant attention within the optimization community, most works focusing on understanding its convergence guarantees assume the strong L-Lipschitz condition. In this work, building on the proposed assumptions by Zhang et al. [2024b] for minimization and Vankov et al.[2024] for VIs, we focus on the more relaxed $\alpha$-symmetric $(L_0, L_1)$-Lipschitz condition. This condition generalizes the standard Lipschitz assumption by allowing the Lipschitz constant to scale with the operator norm, providing a more refined characterization of problem structures in modern machine learning. Under the $\alpha$-symmetric $(L_0, L_1)$-Lipschitz condition, we propose a novel step size strategy for EG to solve root-finding problems and establish sublinear convergence rates for monotone operators and linear convergence rates for strongly monotone operators. Additionally, we prove local convergence guarantees for weak Minty operators. We supplement our analysis with experiments validating our theory and demonstrating the effectiveness and robustness of the proposed step sizes for EG.

Related papers

• Regularized Online RLHF with Generalized Bilinear Preferences [68.44113000390544]
  We consider the problem of contextual online RLHF with general preferences.<n>We adopt the Generalized Bilinear Preference Model to capture preferences via low-rank, skew-symmetric matrices.<n>We prove that the dual gap of the greedy policy is bounded by the square of the estimation error.
  arXiv  Detail & Related papers  (2026-02-26T15:27:53Z)
• On the Convergence Rate of LoRA Gradient Descent [22.183624306817563]
  We present a non-asymptotic convergence analysis of the textitoriginal LoRA gradient descent algorithm.<n>We prove that LoRA gradient descent converges to a stationary point at rate $O(frac1log T)$, where $T$ is the number of iterations.
  arXiv  Detail & Related papers  (2025-12-20T07:20:54Z)
• Convergence Rate Analysis of LION [54.28350823319057]
  LION converges iterations of $cal(sqrtdK-)$ measured by gradient Karush-Kuhn-T (sqrtdK-)$. We show that LION can achieve lower loss and higher performance compared to standard SGD.
  arXiv  Detail & Related papers  (2024-11-12T11:30:53Z)
• Revisiting Inexact Fixed-Point Iterations for Min-Max Problems: Stochasticity and Structured Nonconvexity [18.427215139020632]
  We show that $1L 1$ can be used to improve some state-of-the-art problems even for a multilevel Carlo iteration. We provide an analysis for inexact Halperness estimators for $1L 1$ when the only hold with respect to a solution is a new $1L 1$ theory.
  arXiv  Detail & Related papers  (2024-02-07T18:22:41Z)
• A Unified Analysis on the Subgradient Upper Bounds for the Subgradient Methods Minimizing Composite Nonconvex, Nonsmooth and Non-Lipschitz Functions [7.972544890243396]
  This paper presents a unified analysis for the proximal subgradient method (Prox-SubGrad) type approach. We are able to relate error-bound conditions, the growth conditions of the subgradients of the objective, and the behavior of the proximal subgradient iterates on some remarkably broad classes of objective functions.
  arXiv  Detail & Related papers  (2023-08-30T23:34:11Z)
• Iterative Reweighted Least Squares Networks With Convergence Guarantees for Solving Inverse Imaging Problems [12.487990897680422]
  We present a novel optimization strategy for image reconstruction tasks under analysis-based image regularization. We parameterize such regularizers using potential functions that correspond to weighted extensions of the $ell_pp$-vector and $mathcalS_pp$ Schatten-matrix quasi-norms. We show that thanks to the convergence guarantees of our proposed minimization strategy, such optimization can be successfully performed with a memory-efficient implicit back-propagation scheme.
  arXiv  Detail & Related papers  (2023-08-10T17:59:46Z)
• A Primal-Dual Approach to Solving Variational Inequalities with General Constraints [54.62996442406718]
  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.
  arXiv  Detail & Related papers  (2022-10-27T17:59:09Z)
• 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)
• KL-Entropy-Regularized RL with a Generative Model is Minimax Optimal [70.15267479220691]
  We consider and analyze the sample complexity of model reinforcement learning with a generative variance-free model. Our analysis shows that it is nearly minimax-optimal for finding an $varepsilon$-optimal policy when $varepsilon$ is sufficiently small.
  arXiv  Detail & Related papers  (2022-05-27T19:39:24Z)
• Extragradient Method: $O(1/K)$ Last-Iterate Convergence for Monotone Variational Inequalities and Connections With Cocoercivity [21.22292220954549]
  Extragradient method (EG) Korpelevich is one of the most popular methods for solving saddle point and variational inequalities problems (VIP) Despite its long history and significant attention in the optimization community, there remain important open questions about convergence of EG.
  arXiv  Detail & Related papers  (2021-10-08T17:16:12Z)
• Large-Scale Methods for Distributionally Robust Optimization [53.98643772533416]
  We prove that our algorithms require a number of evaluations gradient independent of training set size and number of parameters. Experiments on MNIST and ImageNet confirm the theoretical scaling of our algorithms, which are 9--36 times more efficient than full-batch methods.
  arXiv  Detail & Related papers  (2020-10-12T17:41:44Z)

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.