Bayes-optimal performance in a discrete space
arXiv:cond-mat/9906356 · doi:10.1088/0305-4470/32/3/010
Abstract
We study a simple model of unsupervised learning where the single symmetry breaking vector has binary components $\pm 1$. 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.
6 pages, 1 figure; small changes