English

Estimate Sequences for Variance-Reduced Stochastic Composite Optimization

Machine Learning 2019-05-08 v1 Machine Learning Optimization and Control

Abstract

In this paper, we propose a unified view of gradient-based algorithms for stochastic convex composite optimization by extending the concept of estimate sequence introduced by Nesterov. This point of view covers the stochastic gradient descent method, variants of the approaches SAGA, SVRG, and has several advantages: (i) we provide a generic proof of convergence for the aforementioned methods; (ii) we show that this SVRG variant is adaptive to strong convexity; (iii) we naturally obtain new algorithms with the same guarantees; (iv) we derive generic strategies to make these algorithms robust to stochastic noise, which is useful when data is corrupted by small random perturbations. Finally, we show that this viewpoint is useful to obtain new accelerated algorithms in the sense of Nesterov.

Keywords

Cite

@article{arxiv.1905.02374,
  title  = {Estimate Sequences for Variance-Reduced Stochastic Composite Optimization},
  author = {Andrei Kulunchakov and Julien Mairal},
  journal= {arXiv preprint arXiv:1905.02374},
  year   = {2019}
}

Comments

short version of preprint arXiv:1901.08788

R2 v1 2026-06-23T08:58:50.975Z