3 papers
cond-mat.dis-nn2001
Retarded Learning: Rigorous Results from Statistical Mechanics
D. Herschkowitz, M. Opper
We study learning of probability distributions characterized by an unknown symmetry direction. Based on an entropic performance measure and the variational method of statistical me…
cond-mat.dis-nn2001
Tractable approximations for probabilistic models: The adaptive TAP mean field approach
Manfred Opper, Ole Winther
We develop an advanced mean field method for approximating averages in probabilistic data models that is based on the TAP approach of disorder physics. In contrast to conventional…
cond-mat.dis-nn1999
Bayes-optimal performance in a discrete space
M. Copelli, C. Van den Broeck, M. Opper
We study a simple model of unsupervised learning where the single symmetry breaking vector has binary components . We calculate exactly the Bayes-optimal performance of an e…