Optimal Algorithms for Stochastic Complementary Composite Minimization - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue SIAM Journal on Optimization Année : 2022

Optimal Algorithms for Stochastic Complementary Composite Minimization

Résumé

Inspired by regularization techniques in statistics and machine learning, we study complementary composite minimization in the stochastic setting. This problem corresponds to the minimization of the sum of a (weakly) smooth function endowed with a stochastic first-order oracle, and a structured uniformly convex (possibly nonsmooth and non-Lipschitz) regularization term. Despite intensive work on closely related settings, prior to our work no complexity bounds for this problem were known. We close this gap by providing novel excess risk bounds, both in expectation and with high probability. Our algorithms are nearly optimal, which we prove via novel lower complexity bounds for this class of problems. We conclude by providing numerical results comparing our methods to the state of the art.

Dates et versions

hal-04230893 , version 1 (06-10-2023)

Identifiants

Citer

Alexandre d'Aspremont, Cristóbal Guzmán, Clément Lezane. Optimal Algorithms for Stochastic Complementary Composite Minimization. SIAM Journal on Optimization, In press. ⟨hal-04230893⟩
18 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More