A Kernel Mean Embedding Approach to Reducing Conservativeness in Stochastic Programming and Control
From MaRDI portal
Publication:6333644
arXiv2001.10398MaRDI QIDQ6333644
Jia-Jie Zhu, Bernhard Schölkopf, Moritz Diehl
Publication date: 28 January 2020
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.
Has companion code repository: https://github.com/jj-zhu/leibniz-ss-2021
This page was built for publication: A Kernel Mean Embedding Approach to Reducing Conservativeness in Stochastic Programming and Control
