A probabilistic interpretation of the constant gain algorithm

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.

MoreLess

Year of publication:	2019-05-19
Authors:	Berardi, Michele

More details

Type of publication:	Book / Working Paper
Language:	English
Notes:	Berardi, Michele (2019): A probabilistic interpretation of the constant gain algorithm.
Classification:	C63 - Computational Techniques ; D83 - Search, Learning, Information and Knowledge ; D84 - Expectations; Speculations ; D90 - Intertemporal Choice and Growth. General
Source:	BASE

Persistent link: https://www.econbiz.de/10015264096