Optimal stochastic approximation algorithms for strongly convex stochastic composite optimization. II: Shrinking procedures and optimal algorithms. (English) Zbl 1293.62167
Summary: In this paper we study new stochastic approximation (SA) type algorithms, namely, the accelerated SA (AC-SA), for solving strongly convex stochastic composite optimization (SCO) problems. Specifically, by introducing a domain shrinking procedure, we significantly improve the large-deviation results associated with the convergence rate of a nearly optimal AC-SA algorithm [the authors, ibid. 22, No. 4, 1469–1492 (2012; Zbl 1301.62077)]. Moreover, we introduce a multistage AC-SA algorithm, which possesses an optimal rate of convergence for solving strongly convex SCO problems in terms of the dependence on not only the target accuracy, but also a number of problem parameters and the selection of initial points. To the best of our knowledge, this is the first time that such an optimal method has been presented in the literature. From our computational results, these AC-SA algorithms can substantially outperform the classical SA and some other SA type algorithms for solving certain classes of strongly convex SCO problems.
MSC:
62L20 | Stochastic approximation |
90C25 | Convex programming |
90C15 | Stochastic programming |
68Q25 | Analysis of algorithms and problem complexity |