English

Machine learning approach to chance-constrained problems: An algorithm based on the stochastic gradient descent

Optimization and Control 2019-05-28 v1

Abstract

We consider chance-constrained problems with discrete random distribution. We aim for problems with a large number of scenarios. We propose a novel method based on the stochastic gradient descent method which performs updates of the decision variable based only on considering a few scenarios. We modify it to handle the non-separable objective. Complexity analysis and a comparison with the standard (batch) gradient descent method is provided. We give three examples with non-convex data and show that our method provides a good solution fast even when the number of scenarios is large.

Keywords

Cite

@article{arxiv.1905.10986,
  title  = {Machine learning approach to chance-constrained problems: An algorithm based on the stochastic gradient descent},
  author = {Lukáš Adam and Martin Branda},
  journal= {arXiv preprint arXiv:1905.10986},
  year   = {2019}
}
R2 v1 2026-06-23T09:25:32.856Z