English

A Stochastic Composite Gradient Method with Incremental Variance Reduction

Optimization and Control 2019-06-26 v1 Machine Learning

Abstract

We consider the problem of minimizing the composition of a smooth (nonconvex) function and a smooth vector mapping, where the inner mapping is in the form of an expectation over some random variable or a finite sum. We propose a stochastic composite gradient method that employs an incremental variance-reduced estimator for both the inner vector mapping and its Jacobian. We show that this method achieves the same orders of complexity as the best known first-order methods for minimizing expected-value and finite-sum nonconvex functions, despite the additional outer composition which renders the composite gradient estimator biased. This finding enables a much broader range of applications in machine learning to benefit from the low complexity of incremental variance-reduction methods.

Keywords

Cite

@article{arxiv.1906.10186,
  title  = {A Stochastic Composite Gradient Method with Incremental Variance Reduction},
  author = {Junyu Zhang and Lin Xiao},
  journal= {arXiv preprint arXiv:1906.10186},
  year   = {2019}
}
R2 v1 2026-06-23T10:02:23.308Z