On-line Non-Convex Constrained Optimization
Optimization and Control
2019-09-18 v1 Machine Learning
Systems and Control
Systems and Control
Abstract
Time-varying non-convex continuous-valued non-linear constrained optimization is a fundamental problem. We study conditions wherein a momentum-like regularising term allow for the tracking of local optima by considering an ordinary differential equation (ODE). We then derive an efficient algorithm based on a predictor-corrector method, to track the ODE solution.
Cite
@article{arxiv.1909.07492,
title = {On-line Non-Convex Constrained Optimization},
author = {Olivier Massicot and Jakub Marecek},
journal= {arXiv preprint arXiv:1909.07492},
year = {2019}
}