Advanced search
Start date
Betweenand
(Reference retrieved automatically from Web of Science through information on FAPESP grant and its corresponding number as mentioned in the publication by the authors.)

Concentration Bounds for Plug-In Estimator of Directed Information

Full text
Author(s):
Ferreira, Ricardo Felipe [1]
Total Authors: 1
Affiliation:
[1] Univ Fed Sao Carlos, Dept Stat, BR-13565905 Sao Carlos - Brazil
Total Affiliations: 1
Document type: Journal article
Source: IEEE TRANSACTIONS ON INFORMATION THEORY; v. 67, n. 8, p. 4939-4947, AUG 2021.
Web of Science Citations: 0
Abstract

In this study, we consider directed information between a pair of jointly stationary ergodic finite-valued chains. Assuming that the jointly process loses memory exponentially fast with a positive constant rate, we obtain concentration bounds for the plug-in estimator of the directed information around its expectation and directed information rate. (AU)

FAPESP's process: 13/07699-0 - Research, Innovation and Dissemination Center for Neuromathematics - NeuroMat
Grantee:Jefferson Antonio Galves
Support Opportunities: Research Grants - Research, Innovation and Dissemination Centers - RIDC
FAPESP's process: 16/12918-0 - Stochastic chains with unbounded memory and application in neuroscience
Grantee:Ricardo Felipe Ferreira
Support Opportunities: Scholarships in Brazil - Doctorate