Deterministic and stochastic primal-dual subgradient algorithms for uniformly convex minimization - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Stochastic Systems Année : 2014

Deterministic and stochastic primal-dual subgradient algorithms for uniformly convex minimization

Résumé

We discuss non-Euclidean deterministic and stochastic algorithms for optimization problems with strongly and uniformly convex objectives. We provide accuracy bounds for the performance of these algorithms and design methods which are adaptive with respect to the parameters of strong or uniform convexity of the objective: in the case when the total number of iterations N is fixed, their accuracy coincides, up to a logarithmic in N factor with the accuracy of optimal algorithms.

Dates et versions

hal-00974231 , version 1 (05-04-2014)

Identifiants

Citer

Anatoli B. Juditsky, Yuri Nesterov. Deterministic and stochastic primal-dual subgradient algorithms for uniformly convex minimization. Stochastic Systems, 2014, 4 (1), pp.44-80. ⟨10.1214/10-SSY010⟩. ⟨hal-00974231⟩
122 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More