Acceleration by Randomization: Randomized First Order Algorithms for Large-scale Convex Optimization - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2009

Acceleration by Randomization: Randomized First Order Algorithms for Large-scale Convex Optimization

Résumé

We discuss the possibility to accelerate solving extremely large-scale well structured convex optimization problems by replacing computationally expensive in the large scale case deterministic first order oracles with their computationally cheap stochastic counterparts and subsequent utilizing state of the art techniques of Convex Stochastic Programming. We show that when medium-accuracy solutions are sought, there are situations where this approach allows to provably outperform the best known deterministic algorithms. This includes solving matrix games and bilinear Nash Equilibrium problems, minimizing convex polynomials over simplexes, recovering signals via L1 minimization, and eigenvalue minimization.
Fichier non déposé

Dates et versions

hal-00981934 , version 1 (23-04-2014)

Identifiants

  • HAL Id : hal-00981934 , version 1

Citer

Anatoli B. Juditsky, Guanghui Lan, Arkadii S. Nemirovski, Alexander Shapiro. Acceleration by Randomization: Randomized First Order Algorithms for Large-scale Convex Optimization. ISMP 2009 - 20th International Symposium of Mathematical Programming, Aug 2009, Chicago, United States. ⟨hal-00981934⟩
275 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More