Related papers: Last-Iterate Guarantees for Learning in Co-coercive Games

Last-Iterate Guarantees for Learning in Co-coercive Games

URL: http://arxiv.org/abs/2604.19065v1
Date: Tue, 21 Apr 2026 04:18:14 GMT
Title: Last-Iterate Guarantees for Learning in Co-coercive Games
Abstract summary: We establish finite-time last-iterate guarantees for vanilla descent in co-coercive games under noisy feedback.<n>This is a broad class of games that is more general than strongly monotone games.
Score: 5.7071219882414885
License: http://creativecommons.org/licenses/by/4.0/
Abstract: We establish finite-time last-iterate guarantees for vanilla stochastic gradient descent in co-coercive games under noisy feedback. This is a broad class of games that is more general than strongly monotone games, allows for multiple Nash equilibria, and includes examples such as quadratic games with negative semidefinite interaction matrices and potential games with smooth concave potentials. Prior work in this setting has relied on relative noise models, where the noise vanishes as iterates approach equilibrium, an assumption that is often unrealistic in practice. We work instead under a substantially more general noise model in which the second moment of the noise is allowed to scale affinely with the squared norm of the iterates, an assumption natural in learning with unbounded action spaces. Under this model, we prove a last-iterate bound of order $O(\log(t)/t^{1/3})$, the first such bound for co-coercive games under non-vanishing noise. We additionally establish almost sure convergence of the iterates to the set of Nash equilibria and derive time-average convergence guarantees.

Related papers

Near-Optimal Last-Iterate Convergence for Zero-Sum Games with Bandit Feedback and Opponent Actions [43.45624707071202]
Last-iterate convergence of learning dynamics in games has attracted significant recent attention.<n>We show that t(-1/2) last-iterate convergence is achievable with high probability in games with bandit feedback.
arXiv Detail & Related papers (2026-05-10T06:23:19Z)
From Average-Iterate to Last-Iterate Convergence in Games: A Reduction and Its Applications [54.49053278073321]
We show that for a large family of games, there exists a simple black-box reduction that transforms the average iterates of an uncoupled learning dynamics into the last iterates of a new uncoupled learning dynamics.<n>Our reduction applies to games where each player's utility is linear in both their own strategy and the joint strategy of all opponents.
arXiv Detail & Related papers (2025-06-04T00:24:14Z)
Revisiting Convergence of AdaGrad with Relaxed Assumptions [4.189643331553922]
We revisit the convergence of AdaGrad with momentum (covering AdaGrad as a special case) on problems. This model encompasses a broad range noises including sub-auau in many practical applications.
arXiv Detail & Related papers (2024-02-21T13:24:14Z)
Adaptively Perturbed Mirror Descent for Learning in Games [10.868347525353293]
We propose a payoff perturbation technique for the Mirror Descent (MD) algorithm in games where the gradient of the payoff functions is monotone. We show that our algorithm exhibits significantly accelerated convergence.
arXiv Detail & Related papers (2023-05-26T04:02:54Z)
On the Convergence of No-Regret Learning Dynamics in Time-Varying Games [89.96815099996132]
We characterize the convergence of optimistic gradient descent (OGD) in time-varying games. Our framework yields sharp convergence bounds for the equilibrium gap of OGD in zero-sum games. We also provide new insights on dynamic regret guarantees in static games.
arXiv Detail & Related papers (2023-01-26T17:25:45Z)
Finding mixed-strategy equilibria of continuous-action games without gradients using randomized policy networks [83.28949556413717]
We study the problem of computing an approximate Nash equilibrium of continuous-action game without access to gradients. We model players' strategies using artificial neural networks. This paper is the first to solve general continuous-action games with unrestricted mixed strategies and without any gradient information.
arXiv Detail & Related papers (2022-11-29T05:16:41Z)
Learning in Multi-Player Stochastic Games [1.0878040851638]
We consider the problem of simultaneous learning in games with many players in the finite-horizon setting. While the typical target solution for a game is a Nash equilibrium, this is intractable with many players. We turn to a different target: algorithms which generate an equilibrium when they are used by all players.
arXiv Detail & Related papers (2022-10-25T19:02:03Z)
Learning Correlated Equilibria in Mean-Field Games [62.14589406821103]
We develop the concepts of Mean-Field correlated and coarse-correlated equilibria. We show that they can be efficiently learnt in emphall games, without requiring any additional assumption on the structure of the game.
arXiv Detail & Related papers (2022-08-22T08:31:46Z)
A unified stochastic approximation framework for learning in games [82.74514886461257]
We develop a flexible approximation framework for analyzing the long-run behavior of learning in games (both continuous and finite) The proposed analysis template incorporates a wide array of popular learning algorithms, including gradient-based methods, exponential/multiplicative weights for learning in finite games, optimistic and bandit variants of the above, etc.
arXiv Detail & Related papers (2022-06-08T14:30:38Z)
From Poincar\'e Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization [49.368421783733815]
We show how adapting the reward can give strong convergence guarantees in monotone games. We also show how this reward adaptation technique can be leveraged to build algorithms that converge exactly to the Nash equilibrium.
arXiv Detail & Related papers (2020-02-19T21:36:58Z)

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