arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.09402cs.LGcs.AIstat.ML
收藏

神经McKean-Vlasov过程:扩散过程中的分布依赖性

Neural McKean-Vlasov Processes: Distributional Dependence in Diffusion Processes

Duke University(杜克大学)

Haoming Yang, Ali Hasan, Yuting Ng, Vahid Tarokh

AI总结:

该研究提出一系列表征McKean-Vlasov随机微分方程的半参数方法及对应参数估计器,实验证明显式纳入分布依赖可有效建模带相互作用的时序数据且保持标准SDE任务性能。

摘要:

McKean-Vlasov随机微分方程(MV-SDEs)通过引入对粒子密度的依赖,为无穷多相互作用粒子的行为提供了数学描述。基于此,我们研究了在SDE参数化中显式纳入分布信息的影响。我们提出了一系列用于表征MV-SDEs的半参数方法,以及基于MV-SDE性质从数据中推断参数的对应估计器。我们分析了不同架构和估计器的特性,并探讨了它们在相关机器学习问题中的适用性。我们在时间序列和概率建模的真实与合成数据集上,对不同架构和估计器的性能进行了实证比较。结果表明,在可交换性假设下,在SDE参数化中显式纳入分布依赖性能有效建模存在相互作用的时序数据,同时由于MV-SDEs关联的概率流类别更丰富,其在标准Itô-SDEs任务上仍能保持优异性能。

英文摘要:

McKean-Vlasov stochastic differential equations (MV-SDEs) provide a mathematical description of the behavior of an infinite number of interacting particles by imposing a dependence on the particle density. As such, we study the influence of explicitly including distributional information in the parameterization of the SDE. We propose a series of semi-parametric methods for representing MV-SDEs, and corresponding estimators for inferring parameters from data based on the properties of the MV-SDE. We analyze the characteristics of the different architectures and estimators, and consider their applicability in relevant machine learning problems. We empirically compare the performance of the different architectures and estimators on real and synthetic datasets for time series and probabilistic modeling. The results suggest that explicitly including distributional dependence in the parameterization of the SDE is effective in modeling temporal data with interaction under an exchangeability assumption while maintaining strong performance for standard Itô-SDEs due to the richer class of probability flows associated with MV-SDEs.

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。

↑