arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.11835cs.GTcs.MAcs.NAmath.NA
收藏

非凸一般和博弈中在n边PL条件下实现全局收敛到纳什均衡

Global Convergence to Nash Equilibrium in Nonconvex General-Sum Games under the $n$-Sided PL Condition

Technical University of Munich(慕尼黑工业大学);Munich Institute of Robotics and Machine Intelligence(慕尼黑机器人与智能研究所)

Yutong Chao, Jalal Etesami

AI总结:

本文提出了一种在非凸一般和博弈中实现全局收敛到纳什均衡的算法,基于n边PL条件扩展了PL条件,并分析了其收敛性及实验性能。

摘要:

我们考虑在一般和博弈中寻找纳什均衡(NE)的问题,其中玩家i的目标函数为f_i(x)=f_i(x_1,...,x_n),其中x_j∈R^{d_j}表示玩家j的策略变量。我们的重点是研究一阶梯度基于算法及其变种,如块坐标下降(BCD)算法,以解决此问题。我们引入了一组称为n边PL条件的条件,该条件扩展了广为人知的梯度主导条件,即Polyak-Łojasiewicz(PL)条件以及多凸性概念。该条件被各种非凸函数满足,使我们能够分析各种梯度下降(GD)算法的收敛性。此外,我们的研究还深入探讨了标准梯度下降方法无法收敛到NE的情况。在这种情况下,我们提出了适应的GD变种,这些变种能够收敛到NE,并分析其收敛速率。最后,我们通过几个实验评估所提出算法的性能。

英文摘要:

We consider the problem of finding a Nash equilibrium (NE) in a general-sum game, where player $i$'s objective is $f_i(x)=f_i(x_1,...,x_n)$, with $x_j\in\mathbb{R}^{d_j}$ denoting the strategy variables of player $j$. Our focus is on investigating first-order gradient-based algorithms and their variations, such as the block coordinate descent (BCD) algorithm, for tackling this problem. We introduce a set of conditions, called the $n$-sided PL condition, which extends the well-established gradient dominance condition a.k.a Polyak-Łojasiewicz (PL) condition and the concept of multi-convexity. This condition, satisfied by various classes of non-convex functions, allows us to analyze the convergence of various gradient descent (GD) algorithms. Moreover, our study delves into scenarios where the standard gradient descent methods fail to converge to NE. In such cases, we propose adapted variants of GD that converge towards NE and analyze their convergence rates. Finally, we evaluate the performance of the proposed algorithms through several experiments.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑