arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.01564cs.LGmath.APmath.OCmath.PR
收藏

平均场Langevin下降-上升的局部指数稳定性及相关粒子系统

Local exponential stability of mean-field Langevin descent-ascent and associated particle system

Pohang University of Science and Technology(浦项科技大学);Korea Advanced Institute of Science and Technology(韩国科学技术院);Université Gustave Eiffel(古斯塔夫·埃菲尔大学)

Geuntaek Seo, Minseop Shin, Pierre Monmarché, Beomjun Choi

AI总结:

研究平均场Langevin下降-上升动力学在Wasserstein空间中的局部指数收敛性,证明混合纳什均衡具有稳健吸引域,且有限粒子系统继承该稳定性至指数时间。

摘要:

我们研究了平均场Langevin下降-上升(MFL-DA),这是一种在概率测度空间上用于熵正则化两人零和游戏的耦合优化动力学,以及其相关的相互作用粒子系统。对于一般的非凸-非凹收益函数,Wang和Chizat(COLT 2024)提出了原始单时间尺度MFL-DA是否收敛到混合纳什均衡以及收敛速率的问题。我们在Wasserstein空间中证明了局部肯定答案:如果初始数据足够接近混合纳什均衡,则平均场动力学以定量速率指数快速收敛到该均衡。我们进一步证明,有限$N$粒子系统在指数时间(关于$N$)内继承这种稳定性,具有与$N$无关的指数速率,但存在有限粒子误差下限。结合Mourrat和Pillaud-Vivien最近关于MFL-DA的反例(表明全局收敛一般不成立),我们的定理完成了Wang-Chizat问题的正面局部部分:混合纳什均衡具有稳健的吸引域,在平均场流及其有限粒子近似下均稳定。

英文摘要:

We study the mean-field Langevin descent-ascent (MFL-DA), a coupled optimization dynamics on the space of probability measures for entropically regularized two-player zero-sum games, together with its associated interacting particle system. For general nonconvex-nonconcave payoffs, Wang and Chizat (COLT 2024) asked whether the original single-timescale MFL-DA converges to the mixed Nash equilibrium and, if so, at what rate. We prove a local affirmative answer in Wasserstein space: if the initial datum is sufficiently close to the mixed Nash equilibrium, then the mean-field dynamics converges to it exponentially fast at a quantitative rate. We further show that the finite-$N$ particle system inherits this stability up to times exponential in $N$, with an $N$-independent exponential rate modulo a finite-particle error floor. Combined with the recent counterexample of Mourrat and Pillaud-Vivien for MFL-DA, which shows that global convergence cannot hold in general, our theorem completes the positive local counterpart of the Wang-Chizat question: the mixed Nash equilibrium has a robust basin of attraction, stable under both the mean-field flow and its finite-particle approximation.

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。

↑