From ɛ-entropy to KL-entropy: Analysis of minimum information complexity density estimation
Zhang, Tong
Ann. Statist., Tome 34 (2006) no. 1, p. 2180-2210 / Harvested from Project Euclid
We consider an extension of ɛ-entropy to a KL-divergence based complexity measure for randomized density estimation methods. Based on this extension, we develop a general information-theoretical inequality that measures the statistical complexity of some deterministic and randomized density estimators. Consequences of the new inequality will be presented. In particular, we show that this technique can lead to improvements of some classical results concerning the convergence of minimum description length and Bayesian posterior distributions. Moreover, we are able to derive clean finite-sample convergence bounds that are not obtainable using previous approaches.
Publié le : 2006-10-14
Classification:  Bayesian posterior distribution,  minimum description length,  density estimation,  62C10,  62G07
@article{1169571794,
     author = {Zhang, Tong},
     title = {From e-entropy to KL-entropy: Analysis of minimum information complexity density estimation},
     journal = {Ann. Statist.},
     volume = {34},
     number = {1},
     year = {2006},
     pages = { 2180-2210},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1169571794}
}
Zhang, Tong. From ɛ-entropy to KL-entropy: Analysis of minimum information complexity density estimation. Ann. Statist., Tome 34 (2006) no. 1, pp.  2180-2210. http://gdmltest.u-ga.fr/item/1169571794/