发表机构
Laboratoire de Mathématiques et Modélisation d’Evry, CNRS, Univ Evry, Université Evry Paris-Saclay; Graduate School of Mathematical Sciences, University of Tokyo; The Institute of Statistical Mathematics(埃夫里数学与建模实验室; 东京大学大学院数理科学研究科; 统计数学研究所)
机构由 AI 辅助整理,请以论文原文为准。AI 中文总结
本文针对随机微分方程中扩散矩阵的非参数估计,提出基于一般函数类的两步估计框架,并建立经验风险与泛化风险之间的通用比较定理,适用于深度神经网络估计器。
AI 中文摘要
我们研究了在具有多维、强混合协变量过程的随机微分方程中扩散矩阵的非参数估计问题。我们提出了一种基于一般函数类的灵活统计框架,该框架不需要线性基表示,从而使我们的结果可直接应用于深度神经网络估计器。我们的方法采用两步估计程序:首先构造一个初步的非参数拟似然估计器,随后通过β-赫尔德类逼近对其进行正则化。我们建立了任意估计器的经验风险与泛化风险之间的一般风险比较定理,而不依赖于底层过程的特定概率结构。在基于时间区间[0,T]上的n+1个观测值进行扩散矩阵学习时,所导出的上界捕捉了与协变量过程混合行为相关的T速率和支配波动率估计的内在n速率之间的内在相互作用。
英文摘要
We investigate the nonparametric estimation of the diffusion matrix in stochastic differential equations featuring multidimensional, strong mixing covariate processes. We propose a flexible statistical framework based on general function classes that does not require a linear basis representation, rendering our results directly applicable to deep neural network estimators. Our approach employs a two-step estimation procedure: constructing a preliminary nonparametric quasi-likelihood estimator and subsequently regularizing it via a $β$-Hölder class approximation. We establish general risk comparison theorems between empirical and generalization risks for arbitrary estimators without relying on a specific probabilistic structure of the underlying process. In diffusion matrix learning based on $n + 1$ observations over the time interval $[0,T]$, the derived upper bounds capture the intrinsic interplay between the $T$-rate, associated with the mixing behavior of the covariate process, and the intrinsic $n$-rate governing the volatility estimation.