Difference between revisions of "Nemenman et al., 2002"
m (1 revision imported)
Latest revision as of 12:28, 4 July 2018
I Nemenman, F Shafee, and W Bialek. "Entropy and inference, revisited." In T. G. Dietterich, S. Becker, and Z. Ghahramani, editors, Adv. Neural Inf. Proc. Syst. 14, Cambridge, MA, 2002. MIT Press. PDF, arXiv.
- 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.