Online Program Home
My Program

Abstract Details

Activity Number: 106 - Recent Trends in Inference from Dynamical Systems
Type: Invited
Date/Time: Monday, July 30, 2018 : 8:30 AM to 10:20 AM
Sponsor: IMS
Abstract #326818 Presentation
Title: Learning from Dynamical Systems
Author(s): Ingo Steinwart*
Companies: University of Stuttgart
Keywords: statistical learning theory; dynamical systems; non-i.i.d. observations; non-parametric classification ; non-parametric regression; system forecasting

Learning algorithms are almost always investigated under the assumption of random samples, where in most cases, the randomness is in form of an i.i.d. process. In this talk I will present some recent results describing when learning is also possible from ergodic dynamical systems, that is, from essentially deterministic time series. Besides some more general consistency results I will mainly focus on certain classes of dynamical systems for which we have a fast decay of correlations for restricted classes of functions. To this end, I will first present a Bernstein-type concentration inequality for such systems. In a second step I will then illustrate the use of this inequality for classification and regression learning from dynamical systems, density estimation, and system forecasting.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2018 program