English

Fast Stochastic Algorithms for Low-rank and Nonsmooth Matrix Problems

Machine Learning 2018-09-28 v1 Optimization and Control Machine Learning

Abstract

Composite convex optimization problems which include both a nonsmooth term and a low-rank promoting term have important applications in machine learning and signal processing, such as when one wishes to recover an unknown matrix that is simultaneously low-rank and sparse. However, such problems are highly challenging to solve in large-scale: the low-rank promoting term prohibits efficient implementations of proximal methods for composite optimization and even simple subgradient methods. On the other hand, methods which are tailored for low-rank optimization, such as conditional gradient-type methods, which are often applied to a smooth approximation of the nonsmooth objective, are slow since their runtime scales with both the large Lipshitz parameter of the smoothed gradient vector and with 1/ϵ1/\epsilon. In this paper we develop efficient algorithms for \textit{stochastic} optimization of a strongly-convex objective which includes both a nonsmooth term and a low-rank promoting term. In particular, to the best of our knowledge, we present the first algorithm that enjoys all following critical properties for large-scale problems: i) (nearly) optimal sample complexity, ii) each iteration requires only a single \textit{low-rank} SVD computation, and iii) overall number of thin-SVD computations scales only with log1/ϵ\log{1/\epsilon} (as opposed to poly(1/ϵ)\textrm{poly}(1/\epsilon) in previous methods). We also give an algorithm for the closely-related finite-sum setting. At the heart of our results lie a novel combination of a variance-reduction technique and the use of a \textit{weak-proximal oracle} which is key to obtaining all above three properties simultaneously.

Keywords

Cite

@article{arxiv.1809.10477,
  title  = {Fast Stochastic Algorithms for Low-rank and Nonsmooth Matrix Problems},
  author = {Dan Garber and Atara Kaplan},
  journal= {arXiv preprint arXiv:1809.10477},
  year   = {2018}
}
R2 v1 2026-06-23T04:20:19.932Z