Sparse Accelerated Exponential Weights - Archive ouverte HAL Access content directly
Conference Papers Year : 2017

Sparse Accelerated Exponential Weights

Abstract

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
Origin : Files produced by the author(s)

Dates and versions

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

Identifiers

  • HAL Id : hal-01376808 , version 1

Cite

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 View
56 Download

Share

Gmail Facebook X LinkedIn More