Mirror averaging with sparsity priors

Abstract : We consider the problem of aggregating the elements of a (possibly infinite) dictionary for building a decision procedure, that aims at minimizing a given criterion. Along with the dictionary, an independent identically distributed training sample is available, on which the performance of a given procedure can be tested. In a fairly general set-up, we establish an oracle inequality for the Mirror Averaging aggregate based on any prior distribution. This oracle inequality is applied in the context of sparse coding for different problems of statistics and machine learning such as regression, density estimation and binary classification.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-00461580
Contributor : Arnak Dalalyan <>
Submitted on : Friday, July 27, 2012 - 12:08:51 AM
Last modification on : Tuesday, May 14, 2019 - 10:39:14 AM
Long-term archiving on : Sunday, October 28, 2012 - 2:35:07 AM

Files

Bernoulli-revised5.pdf
Files produced by the author(s)

Identifiers

Citation

Arnak S. Dalalyan, Alexandre Tsybakov. Mirror averaging with sparsity priors. Bernoulli, Bernoulli Society for Mathematical Statistics and Probability, 2012, 18 (3), pp.914-944. ⟨10.3150/11-BEJ361⟩. ⟨hal-00461580v3⟩

Share

Metrics

Record views

596

Files downloads

337