English

Accelerating Stochastic Sequential Quadratic Programming for Equality Constrained Optimization using Predictive Variance Reduction

Optimization and Control 2023-03-28 v3

Abstract

In this paper, we propose a stochastic method for solving equality constrained optimization problems that utilizes predictive variance reduction. Specifically, we develop a method based on the sequential quadratic programming paradigm that employs variance reduction in the gradient approximations. Under reasonable assumptions, we prove that a measure of first-order stationarity evaluated at the iterates generated by our proposed algorithm converges to zero in expectation from arbitrary starting points, for both constant and adaptive step size strategies. Finally, we demonstrate the practical performance of our proposed algorithm on constrained binary classification problems that arise in machine learning.

Keywords

Cite

@article{arxiv.2204.04161,
  title  = {Accelerating Stochastic Sequential Quadratic Programming for Equality Constrained Optimization using Predictive Variance Reduction},
  author = {Albert S. Berahas and Jiahao Shi and Zihong Yi and Baoyu Zhou},
  journal= {arXiv preprint arXiv:2204.04161},
  year   = {2023}
}

Comments

42 pages, 5 figures, 4 tables