Learning by mirror averaging

  title={Learning by mirror averaging},
  author={Anatoli Juditsky and Philippe Rigollet and Alexandre B. Tsybakov},
Given a collection of M different estimators or classifiers, we study the problem of model selection type aggregation, i.e., we construct a new estimator or classifier, called aggregate, which is nearly as good as the best among them with respect to a given risk criterion. We define our aggregate by a simple recursive procedure which solves an auxiliary stochastic linear programming problem related to the original non-linear one and constitutes a special case of the mirror averaging algorithm… CONTINUE READING
Highly Influential
This paper has highly influenced 10 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 101 citations. REVIEW CITATIONS

From This Paper

Topics from this paper.


Publications citing this paper.
Showing 1-10 of 71 extracted citations

Fast rates in statistical and online learning

Journal of Machine Learning Research • 2015
View 16 Excerpts
Highly Influenced

Hyper-Sparse Optimal Aggregation

Journal of Machine Learning Research • 2011
View 6 Excerpts
Highly Influenced

102 Citations

Citations per Year
Semantic Scholar estimates that this publication has 102 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 31 references

Statistical Learning Theory and Stochastic Optimization

O. Catoni
Ecole d’Eté de Probabilités de Saint-Flour XXXI - • 2004
View 8 Excerpts
Highly Influenced

Universal ” aggregation rules with exact bias bounds

O. Catoni
Preprint 510 , Laboratoire de Probabilités et Modèles Aléatoires , Univ . Paris 6 and Paris 7 • 1999
View 6 Excerpts
Highly Influenced

Mixing Strategies for Density Estimation

View 3 Excerpts
Highly Influenced

Saint-Flour Lecture Notes

P. Massart
Ecole d’Eté de Probabilités de Saint-Flour XXXIII - • 2006
View 1 Excerpt
Highly Influenced

Local likelihood modeling via stagewise aggregation

D. Belomestny, V. Spokoiny
Preprint n. 1000. WIAS-Berlin • 2004
View 1 Excerpt
Highly Influenced

Aggregation for Gaussian regression

F. Bunea, A. B. Tsybakov, M. H. Wegkamp
Ann . Statist . • 2007

Spatial aggregation of local likelihood estimates with applications to classification

D. Belomestny, V. Spokoiny
Ann . Statist . • 2007

Similar Papers

Loading similar papers…