A Kernel Mean Embedding Approach to Reducing Conservativeness in Stochastic Programming and Control
Optimization and Control
2020-04-24 v2 Machine Learning
Systems and Control
Systems and Control
Abstract
We apply kernel mean embedding methods to sample-based stochastic optimization and control. Specifically, we use the reduced-set expansion method as a way to discard sampled scenarios. The effect of such constraint removal is improved optimality and decreased conservativeness. This is achieved by solving a distributional-distance-regularized optimization problem. We demonstrated this optimization formulation is well-motivated in theory, computationally tractable and effective in numerical algorithms.
Cite
@article{arxiv.2001.10398,
title = {A Kernel Mean Embedding Approach to Reducing Conservativeness in Stochastic Programming and Control},
author = {Jia-Jie Zhu and Moritz Diehl and Bernhard Schölkopf},
journal= {arXiv preprint arXiv:2001.10398},
year = {2020}
}