arXiv · cond-mat/9906356
Bayes-optimal performance in a discrete space
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.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
M. Copelli, C. Van den Broeck, M. Opper. 1999-11-10. Bayes-optimal performance in a discrete space. https://doi.org/10.1088/0305-4470%2F32%2F3%2F010
Cite the original work for its findings. Save a collection to share your selection of sources.