Field Theoretical Analysis of On-line Learning of Probability Distributions

Preprint

30 November 1999

preprint
Published by arXiv in arXiv

https://doi.org/10.48550/arXiv.cond-mat/9911474

Abstract

On-line learning of probability distributions is analyzed from the field theoretical point of view. We can obtain an optimal on-line learning algorithm, since renormalization group enables us to control the number of degrees of freedom of a system according to the number of examples. We do not learn parameters of a model, but probability distributions themselves. Therefore, the algorithm requires no a priori knowledge of a model.

Keywords

PROBABILITY DISTRIBUTIONS
LEARNING OF PROBABILITY
DEGREES OF FREEDOM
FIELD THEORETICAL
LINE LEARNING
THEORETICAL
ALGORITHM
KNOWLEDGE

All Related Versions

Version 1, 1999-11-30, ArXiv
Published version: Physical Review Letters, 83 (17), 3554.

This publication has 0 references indexed in Scilit: