Retarded Learning: Rigorous Results from Statistical Mechanics
Disordered Systems and Neural Networks
2009-11-07 v1
Abstract
We study learning of probability distributions characterized by an unknown symmetry direction. Based on an entropic performance measure and the variational method of statistical mechanics we develop exact upper and lower bounds on the scaled critical number of examples below which learning of the direction is impossible. The asymptotic tightness of the bounds suggests an asymptotically optimal method for learning nonsmooth distributions.
Cite
@article{arxiv.cond-mat/0103275,
title = {Retarded Learning: Rigorous Results from Statistical Mechanics},
author = {D. Herschkowitz and M. Opper},
journal= {arXiv preprint arXiv:cond-mat/0103275},
year = {2009}
}
Comments
8 pages, 1 figure