Translator Disclaimer
August 2020 Empirical risk minimization and complexity of dynamical models
Kevin McGoff, Andrew B. Nobel
Ann. Statist. 48(4): 2031-2054 (August 2020). DOI: 10.1214/19-AOS1876

Abstract

A dynamical model consists of a continuous self-map $T:\mathcal{X}\to \mathcal{X}$ of a compact state space $\mathcal{X}$ and a continuous observation function $f:\mathcal{X}\to \mathbb{R}$. This paper considers the fitting of a parametrized family of dynamical models to an observed real-valued stochastic process using empirical risk minimization. The limiting behavior of the minimum risk parameters is studied in a general setting. We establish a general convergence theorem for minimum risk estimators and ergodic observations. We then study conditions under which empirical risk minimization can effectively separate signal from noise in an additive observational noise model. The key condition in the latter results is that the family of dynamical models has limited complexity, which is quantified through a notion of entropy for families of infinite sequences that connects covering number based entropies with topological entropy studied in dynamical systems. We establish close connections between entropy and limiting average mean widths for stationary processes, and discuss several examples of dynamical models.

Citation

Download Citation

Kevin McGoff. Andrew B. Nobel. "Empirical risk minimization and complexity of dynamical models." Ann. Statist. 48 (4) 2031 - 2054, August 2020. https://doi.org/10.1214/19-AOS1876

Information

Received: 1 December 2016; Revised: 1 May 2019; Published: August 2020
First available in Project Euclid: 14 August 2020

MathSciNet: MR4134785
Digital Object Identifier: 10.1214/19-AOS1876

Subjects:
Primary: 62M09

Rights: Copyright © 2020 Institute of Mathematical Statistics

JOURNAL ARTICLE
24 PAGES

This article is only available to subscribers.
It is not available for individual sale.
+ SAVE TO MY LIBRARY

SHARE
Vol.48 • No. 4 • August 2020
Back to Top