Corpus ID: 210932479

A Kernel Mean Embedding Approach to Reducing Conservativeness in Stochastic Programming and Control

@article{Zhu2020AKM,
  title={A Kernel Mean Embedding Approach to Reducing Conservativeness in Stochastic Programming and Control},
  author={Jia-Jie Zhu and Bernhard Sch{\"o}lkopf and Moritz Diehl},
  journal={ArXiv},
  year={2020},
  volume={abs/2001.10398}
}
  • Jia-Jie Zhu, Bernhard Schölkopf, Moritz Diehl
  • Published 2020
  • Mathematics, Computer Science, Engineering
  • ArXiv
  • 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… CONTINUE READING

    Citations

    Publications citing this paper.

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 21 REFERENCES

    The scenario approach to robust control design

    VIEW 1 EXCERPT

    Super-Samples from Kernel Herding

    VIEW 1 EXCERPT