A1774
Title: Deep neural networks estimation for dependent data
Authors: Chao Zheng - University of Southampton (United Kingdom) [presenting]
Gan Yuan - City University of Hong Kong (Hong Kong)
Zudi Lu - City University of Hong Kong (China)
Shubin Wu - University of Southampton (United Kingdom)
Abstract: Recent years have seen substantial progress in the theoretical analysis of deep neural networks, though the majority of existing results assume independent observations. In contrast, the statistical properties of deep ReLU neural networks for modelling nonlinear, non-i.i.d. mixing sequences are investigated, encompassing a broad class of time series models. Sharp non-asymptotic error bounds for the DNN estimator are established, demonstrating that these bounds depend explicitly on the underlying dependence structure of the data, the architectural characteristics of the network, and the dependence structure under different mixing scenarios. Systematic simulation studies demonstrate that the empirical results align closely with the theoretical findings.
