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.
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}
}