Sparse Accelerated Exponential Weights - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Sparse Accelerated Exponential Weights

Résumé

We consider the stochastic optimization problem where a convex function is minimized observing recursively the gradients. We introduce SAEW, a new procedure that accelerates exponential weights procedures with the slow rate 1/ √ T to procedures achieving the fast rate 1/T. Under the strong convexity of the risk, we achieve the optimal rate of convergence for approximating sparse parameters in R^d. The acceleration is achieved by using successive averaging steps in an online fashion. The procedure also produces sparse estimators thanks to additional hard threshold steps.
Fichier principal
Vignette du fichier
GaillardWintenberger2016-SAEW.pdf (1.39 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-01376808 , version 1 (17-10-2016)

Identifiants

  • HAL Id : hal-01376808 , version 1

Citer

Pierre Gaillard, Olivier Wintenberger. Sparse Accelerated Exponential Weights. 20th International Conference on Artificial Intelligence and Statistics (AISTATS), Apr 2017, Fort Lauderdale, United States. ⟨hal-01376808⟩
204 Consultations
59 Téléchargements

Partager

Gmail Facebook X LinkedIn More