English

Bayes-optimal performance in a discrete space

Disordered Systems and Neural Networks 2009-10-31 v3

Abstract

We study a simple model of unsupervised learning where the single symmetry breaking vector has binary components ±1\pm 1. We calculate exactly the Bayes-optimal performance of an estimator which is required to lie in the same discrete space. We also show that, except for very special cases, such an estimator cannot be obtained by minimization of a class of variationally optimal potentials.

Keywords

Cite

@article{arxiv.cond-mat/9906356,
  title  = {Bayes-optimal performance in a discrete space},
  author = {M. Copelli and C. Van den Broeck and M. Opper},
  journal= {arXiv preprint arXiv:cond-mat/9906356},
  year   = {2009}
}

Comments

6 pages, 1 figure; small changes