Physics – Data Analysis – Statistics and Probability
Scientific paper
2001-08-15
Advances in Neural Information Processing Systems 14, 2002. MIT Press
Physics
Data Analysis, Statistics and Probability
LaTex2e, 9 pages, 5 figures; references added, minor revisions introduced, formatting errors corrected
Scientific paper
We study properties of popular near-uniform (Dirichlet) priors for learning undersampled probability distributions on discrete nonmetric spaces and show that they lead to disastrous results. However, an Occam-style phase space argument expands the priors into their infinite mixture and resolves most of the observed problems. This leads to a surprisingly good estimator of entropies of discrete distributions.
Bialek William
Nemenman Ilya
Shafee Fariel
No associations
LandOfFree
Entropy and inference, revisited does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Entropy and inference, revisited, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Entropy and inference, revisited will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-136082