We study the mean-field limit of the stochastic interacting particle systems via tools from information theory. The key in our method is that, after applying the data processing inequality, one only needs to handle independent copies of solutions to the mean-field McKean stochastic differential equations, which then allows one to apply the law of large numbers. Our result on the propagation of chaos in path space is valid for both first and second order interacting particle systems; in particular, for the latter one our convergence rate is independent of the particle mass and also only linear in time. Our framework is different from current approaches in literature and could provide new insight for the study of interacting particle systems.

翻译：我们借助信息论工具研究随机交互粒子系统的平均场极限。该方法的关键在于，应用数据处理不等式后，只需处理平均场McKean随机微分方程解的独立副本，进而可以运用大数定律。我们关于路径空间中混沌传播的结果对一阶和二阶交互粒子系统均成立；特别地，对于二阶系统，收敛速率与粒子质量无关且仅随时间线性增长。这一框架与文献中现有方法不同，可为交互粒子系统的研究提供新见解。