arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2511.09112math.OC
收藏

随机环境下McKean-Vlasov前向-后向随机微分方程的深度签名方法

Deep Signature Approach for McKean-Vlasov FBSDEs in a Random Environment

University of California, Santa Barbara(加州大学圣塔芭芭拉分校);Shanghai Center for Data Science(上海数据科学中心;纽约大学上海校区华东师范大学数学科学研究所;纽约大学上海校区);NYU-ECNU Institute of Mathematical Sciences at NYU Shanghai(香港中文大学);NYU Shanghai;The Chinese University of Hong Kong

Ruimeng Hu, Botao Jin, Mathieu Laurière, Jiacheng Zhang

AI总结:

针对含共同噪声且系数依赖状态条件分布的McKean-Vlasov前向-后向随机微分方程,提出基于深度学习和虚拟博弈的算法,用签名表示条件分布并通过监督学习更新,实现高维可扩展性且经实验验证有效。

摘要:

含共同噪声的平均场博弈为建模受共享随机性影响的大规模群体集体行为提供了强大框架,例如金融中的系统性风险或经济学中的环境冲击。这些问题可重构为随机环境下的McKean-Vlasov前向-后向随机微分方程(MV-FBSDEs),其中系数依赖于给定共同噪声下状态的条件分布。然而,现有数值方法很大程度上局限于相互作用仅依赖于期望或低阶矩的情况,因此无法解决完全分布依赖的一般情形。在这项工作中,我们提出一种基于深度学习的算法,用于求解含共同噪声和一般平均场相互作用的MV-FBSDEs。基于虚拟博弈,我们的方法迭代求解具有固定分布的条件FBSDEs,其中条件分布使用签名进行高效表示,然后通过监督学习更新分布。深度神经网络既用于求解条件FBSDEs,也用于近似分布依赖的系数,从而实现对高维问题的可扩展性。在适当假设下,我们建立了虚拟博弈迭代的收敛性,误差由监督学习步骤控制。包括含共同噪声的分布依赖平均场博弈在内的数值实验证明了所提方法的有效性。

英文摘要:

Mean-field games with common noise provide a powerful framework for modeling the collective behavior of large populations subject to shared randomness, such as systemic risk in finance or environmental shocks in economics. These problems can be reformulated as McKean-Vlasov forward-backward stochastic differential equations (MV-FBSDEs) in a random environment, where the coefficients depend on the conditional law of the state given the common noise. Existing numerical methods, however, are largely limited to cases where interactions depend only on expectations or low-order moments, and therefore cannot address the general setting of full distributional dependence. In this work, we introduce a deep learning-based algorithm for solving MV-FBSDEs with common noise and general mean-field interactions. Building on fictitious play, our method iteratively solves conditional FBSDEs with fixed distributions, where the conditional law is efficiently represented using signatures, and then updates the distribution through supervised learning. Deep neural networks are employed both to solve the conditional FBSDEs and to approximate the distribution-dependent coefficients, enabling scalability to high-dimensional problems. Under suitable assumptions, we establish convergence in terms of the fictitious play iterations, with error controlled by the supervised learning step. Numerical experiments, including a distribution-dependent mean-field game with common noise, demonstrate the effectiveness of the proposed approach.

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。

↑