Stochastic Mirror Descent for Large-Scale Sparse Recovery - Centre de Recherche en Économie et Statistique Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Stochastic Mirror Descent for Large-Scale Sparse Recovery

Résumé

In this paper we discuss an application of Stochastic Approximation to statistical estimation of highdimensional sparse parameters. The proposed solution reduces to resolving a penalized stochastic optimization problem on each stage of a multistage algorithm; each problem being solved to a prescribed accuracy by the non-Euclidean Composite Stochastic Mirror Descent (CSMD) algorithm. Assuming that the problem objective is smooth and quadratically minorated and stochastic perturbations are sub-Gaussian, our analysis prescribes the method parameters which ensure fast convergence of the estimation error (the radius of a confidence ball of a given norm around the approximate solution). This convergence is linear during the first "preliminary" phase of the routine and is sublinear during the second "asymptotic" phase. We consider an application of the proposed approach to sparse Generalized Linear Regression problem. In this setting, we show that the proposed algorithm attains the optimal convergence of the estimation error under weak assumptions on the regressor distribution. We also present a numerical study illustrating the performance of the algorithm on high-dimensional simulation data.
Fichier principal
Vignette du fichier
Stochastic_Mirror_Descent_for_Large_Scale_Sparse_Recovery_Arxiv_final.pdf (1.5 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03826176 , version 1 (24-10-2022)

Identifiants

  • HAL Id : hal-03826176 , version 1

Citer

Yannis Bekri, Sasila Ilandarideva, Anatoli B. Juditsky, Vianney Perchet. Stochastic Mirror Descent for Large-Scale Sparse Recovery. AISTATS - 2023 - 26th International Conference on Artificial Intelligence and Statistics, Apr 2023, Valencia, Spain. ⟨hal-03826176⟩
73 Consultations
67 Téléchargements

Partager

Gmail Facebook X LinkedIn More