Entropy and inference, revisited
| dc.creator | Nemenman, Ilya | |
| dc.creator | Shafee, Fariel | |
| dc.creator | Bialek, William | |
| dc.date | 2001-08-15 | |
| dc.date | 2002-01-09 | |
| dc.date.accessioned | 2026-07-07T05:46:11Z | |
| dc.date.available | 2026-07-07T05:46:11Z | |
| dc.description | 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. | |
| dc.description | LaTex2e, 9 pages, 5 figures; references added, minor revisions introduced, formatting errors corrected | |
| dc.identifier | https://arxiv.org/abs/physics/0108025 | |
| dc.identifier | http://arxiv.org/abs/physics/0108025 | |
| dc.identifier | Advances in Neural Information Processing Systems 14, 2002. MIT Press | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/84251 | |
| dc.subject | Data Analysis, Statistics and Probability | |
| dc.title | Entropy and inference, revisited | |
| dc.type | text |