A probabilistic interpretation of the constant gain algorithm

Research output: Working paper

Abstract

This paper proposes a novel interpretation of the constant gain learning algorithm through a probabilistic setting with Bayesian updating. Such framework allows to understand the gain coefficient in terms of the probability of changes in the estimated quantity.
Original languageEnglish
PublisherUniversity Library of Munich
Publication statusPublished - 2019

Publication series

NameMPRA
PublisherUniversity Library of Munich, Germany
No.94023

Fingerprint

Dive into the research topics of 'A probabilistic interpretation of the constant gain algorithm'. Together they form a unique fingerprint.

Cite this