Adaptive deep learning for nonlinear time series models

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kurisu, Daisuke, Fukami, Riku, Koike, Yuta
Formato: Preprint
Publicado: 2022
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917655958519808
author Kurisu, Daisuke
Fukami, Riku
Koike, Yuta
author_facet Kurisu, Daisuke
Fukami, Riku
Koike, Yuta
contents In this paper, we develop a general theory for adaptive nonparametric estimation of the mean function of a non-stationary and nonlinear time series model using deep neural networks (DNNs). We first consider two types of DNN estimators, non-penalized and sparse-penalized DNN estimators, and establish their generalization error bounds for general non-stationary time series. We then derive minimax lower bounds for estimating mean functions belonging to a wide class of nonlinear autoregressive (AR) models that include nonlinear generalized additive AR, single index, and threshold AR models. Building upon the results, we show that the sparse-penalized DNN estimator is adaptive and attains the minimax optimal rates up to a poly-logarithmic factor for many nonlinear AR models. Through numerical simulations, we demonstrate the usefulness of the DNN methods for estimating nonlinear AR models with intrinsic low-dimensional structures and discontinuous or rough mean functions, which is consistent with our theory.
format Preprint
id arxiv_https___arxiv_org_abs_2207_02546
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Adaptive deep learning for nonlinear time series models
Kurisu, Daisuke
Fukami, Riku
Koike, Yuta
Statistics Theory
Machine Learning
In this paper, we develop a general theory for adaptive nonparametric estimation of the mean function of a non-stationary and nonlinear time series model using deep neural networks (DNNs). We first consider two types of DNN estimators, non-penalized and sparse-penalized DNN estimators, and establish their generalization error bounds for general non-stationary time series. We then derive minimax lower bounds for estimating mean functions belonging to a wide class of nonlinear autoregressive (AR) models that include nonlinear generalized additive AR, single index, and threshold AR models. Building upon the results, we show that the sparse-penalized DNN estimator is adaptive and attains the minimax optimal rates up to a poly-logarithmic factor for many nonlinear AR models. Through numerical simulations, we demonstrate the usefulness of the DNN methods for estimating nonlinear AR models with intrinsic low-dimensional structures and discontinuous or rough mean functions, which is consistent with our theory.
title Adaptive deep learning for nonlinear time series models
topic Statistics Theory
Machine Learning
url https://arxiv.org/abs/2207.02546