Aggregation by exponential weighting and sharp oracle inequalities
作者： Arnak S. Dalalyan , Alexandre B. Tsybakov
DOI: 10.1007/978-3-540-72927-3_9
关键词:
摘要: In the present paper, we study problem of aggregation under squared loss in model regression with deterministic design. We obtain sharp oracle inequalities for convex aggregates defined via exponential weights, general assumptions on distribution errors and functions to aggregate. show how these results can be applied derive a sparsity inequality.
springer.com
archives-ouvertes.fr
crest.fr 
acm.org 参考文章(35)
Jean-Yves Audibert, Théorie statistique de l'apprentissage : une approche PAC-Bayésienne Paris 6. ,(2004)
Olivier Catoni, Statistical learning theory and stochastic optimization Springer Berlin Heidelberg. ,(2004) , 10.1007/B99352
Olivier Catoni, École d'été de probabilités de Saint-Flour, Jean Picard, Statistical learning theory and stochastic optimization : École d'eté de probabilités de Saint-Flour XXXI - 2001 Springer. ,(2004)
V. A. Statulevičius, I︠u︡. V. Prokhorov, Limit Theorems of Probability Theory ,(2000)
Marc Yor, Daniel Revuz, Continuous martingales and Brownian motion ,(1990)
Florentina Bunea, Alexandre B. Tsybakov, Marten H. Wegkamp, Aggregation and Sparsity Via ℓ1 Penalized Least Squares Learning Theory. pp. 379- 391 ,(2006) , 10.1007/11776420_29
Nicolo Cesa-Bianchi, Gabor Lugosi, Prediction, learning, and games ,(2006)
Jean-Yves Audibert, A Randomized Online Learning Algorithm for Better Variance Control Learning Theory. pp. 392- 407 ,(2006) , 10.1007/11776420_30
Alexandre B. Tsybakov, Optimal Rates of Aggregation Learning Theory and Kernel Machines. pp. 303- 313 ,(2003) , 10.1007/978-3-540-45167-9_23
Yuhong Yang, Adaptive Regression by Mixing Journal of the American Statistical Association. ,vol. 96, pp. 574- 588 ,(2001) , 10.1198/016214501753168262