A Kernel Mean Embedding Approach to Reducing Conservativeness in Stochastic Programming and Control
Abstract
In this paper, 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
Text
Zhu et al. "A Kernel Mean Embedding Approach to Reducing Conservativeness in Stochastic Programming and Control." Proceedings of the 2nd Conference on Learning for Dynamics and Control, 2020.Markdown
[Zhu et al. "A Kernel Mean Embedding Approach to Reducing Conservativeness in Stochastic Programming and Control." Proceedings of the 2nd Conference on Learning for Dynamics and Control, 2020.](https://mlanthology.org/l4dc/2020/zhu2020l4dc-kernel/)BibTeX
@inproceedings{zhu2020l4dc-kernel,
title = {{A Kernel Mean Embedding Approach to Reducing Conservativeness in Stochastic Programming and Control}},
author = {Zhu, Jia-Jie and Schoelkopf, Bernhard and Diehl, Moritz},
booktitle = {Proceedings of the 2nd Conference on Learning for Dynamics and Control},
year = {2020},
pages = {915-923},
volume = {120},
url = {https://mlanthology.org/l4dc/2020/zhu2020l4dc-kernel/}
}