Near-Optimal Bayesian Ambiguity Sets for Distributionally Robust Optimization

@inproceedings{Gupta2016NearOptimalBA,
  title={Near-Optimal Bayesian Ambiguity Sets for Distributionally Robust Optimization},
  author={Vishal Gupta},
  year={2016}
}
We propose a Bayesian framework for assessing the relative strengths of data-driven ambiguity sets in distributionally robust optimization (DRO) when the underlying distribution is defined by a finite-dimensional parameter. The key idea is to measure the relative size between a candidate ambiguity set and a specific, asymptotically optimal set. This asymptotically optimal set is provably the smallest convex ambiguity set that satisfies a particular Bayesian robustness guarantee with respect to… CONTINUE READING
1 Citations
44 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-10 of 44 references

Nonparametric bernstein–von mises theorems in gaussian white

  • 206–237. Castillo, Ismaël, Richard Nickl
  • 2013
Highly Influential
4 Excerpts

Mathematical Theory of Inventory and Production

  • Shapiro, Alexander, Darinka Dentcheva, P. RuszczyĹ, Andrzej
  • 2014
Highly Influential
2 Excerpts

A bernstein-von mises theorem in the nonparametric right-censoring

  • 1287msom.1.1.50. Kim, Yongdai, Jaeyong Lee
  • 2004
Highly Influential
2 Excerpts

Similar Papers

Loading similar papers…