Please use this identifier to cite or link to this item:
Title: Measures of distinguishability between stochastic processes
Authors: Yang, Chengran
Binder, Felix C.
Gu, Mile
Elliott, Thomas J.
Keywords: Science::Physics
Issue Date: 2020
Source: Yang, C., Binder, F. C., Gu, M., & Elliott, T. J. (2020). Measures of distinguishability between stochastic processes. Physical Review E, 101(6), 062137-. doi:10.1103/physreve.101.062137
Project: NRF-NRFF2016-02
Journal: Physical Review E 
Abstract: Quantifying how distinguishable two stochastic processes are is at the heart of many fields, such as machine learning and quantitative finance. While several measures have been proposed for this task, none have universal applicability and ease of use. In this article, we suggest a set of requirements for a well-behaved measure of process distinguishability. Moreover, we propose a family of measures, called divergence rates, that satisfy all of these requirements. Focusing on a particular member of this family—the coemission divergence rate—we show that it can be computed efficiently, behaves qualitatively similar to other commonly used measures in their regimes of applicability, and remains well behaved in scenarios where other measures break down.
ISSN: 2470-0045
DOI: 10.1103/PhysRevE.101.062137
Rights: © 2020 American Physical Society (APS). All rights reserved. This paper was published in Physical Review E and is made available with permission of American Physical Society (APS).
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SPMS Journal Articles

Files in This Item:
File Description SizeFormat 
PhysRevE.101.062137.pdf920.96 kBAdobe PDFView/Open

Page view(s)

Updated on Mar 3, 2021

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.