Optimal Kullback-Leibler Aggregation in Mixture Estimation by Maximum Likelihood

Arnak Dalalyan and Mehdi Sebbar ()
Additional contact information
Mehdi Sebbar: CREST;ENSAE

No 2017-22, Working Papers from Center for Research in Economics and Statistics

Abstract: We study the maximum likelihood estimator of density of n independent observations, under the assumption that it is well approximated by a mixture with a large number of components. The main focus is on statistical properties with respect to the Kullback-Leibler loss. We establish risk bounds taking the form of sharp oracle inequalities both in deviation and in expectation. A simple consequence of these bounds is that the maximum likelihood estimator attains the optimal rate ((logK)/n)^1/2, up to a possible logarithmic correction, in the problem of convex aggregation when the number K of components is larger than n^1/2. More importantly, under the additional assumption that the Gram matrix of the components satisfies the compatibility condition, the obtained oracle inequalities yield the optimal rate in the sparsity scenario. That is, if the weight vector is (nearly) D-sparse, we get the rate (D logK)/n. As a natural complement to our oracle inequalities, we introduce the notion of nearly-D-sparse aggregation and establish matching lower bounds for this type of aggregation.

Pages: 29 pages
Date: 2017-01-19
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://crest.science/RePEc/wpstorage/2017-22.pdf CREST working paper version (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:crs:wpaper:2017-22

Access Statistics for this paper

More papers in Working Papers from Center for Research in Economics and Statistics Contact information at EDIRC.
Bibliographic data for series maintained by Secretariat General () and Murielle Jules Maintainer-Email : murielle.jules@ensae.Fr.