Munich Personal RePEc Archive

A probabilistic interpretation of the constant gain algorithm

Berardi, Michele (2019): A probabilistic interpretation of the constant gain algorithm.

[img] PDF
MPRA_paper_94023.pdf

Download (135kB)

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.

UB_LMU-Logo
MPRA is a RePEc service hosted by
the Munich University Library in Germany.