Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization I: A Generic Algorithmic Framework

• Published in: SIAM journal on optimization Vol. 22; no. 4; pp. 1469 - 1492
• Main Authors: Ghadimi, Saeed, Lan, Guanghui
• Format: Journal Article
• Language: English
• Published: Philadelphia Society for Industrial and Applied Mathematics 01.01.2012
• Subjects: Algorithms; Approximation; Complexity theory; Convex analysis; Methods; Optimization; Random variables; Signal processing

In this paper we present a generic algorithmic framework, namely, the accelerated stochastic approximation (AC-SA) algorithm, for solving strongly convex stochastic composite optimization (SCO) problems. While the classical stochastic approximation algorithms are asymptotically optimal for solving d...