Data-Driven Chance Constrained Programs over Wasserstein Balls
Zhi Chen (zhi.chenimperial.ac.uk)
Abstract: We provide an exact deterministic reformulation for data-driven chance constrained programs over Wasserstein balls. For individual chance constraints as well as joint chance constraints with right-hand side uncertainty, our reformulation amounts to a mixed-integer conic program. In the special case of a Wasserstein ball with the $1$-norm or the $\infty$-norm, the cone is the nonnegative orthant, and the chance constrained program can be reformulated as a mixed-integer linear program. Using our reformulation, we show that two popular approximation schemes based on the conditional-value-at-risk and the Bonferroni inequality can perform poorly in practice and that these two schemes are generally incomparable with each other.
Keywords: Distributionally robust optimization, ambiguous chance constraints, Wasserstein distance.
Category 1: Robust Optimization
Category 2: Stochastic Programming
Category 3: Integer Programming ((Mixed) Integer Nonlinear Programming )
Entry Submitted: 06/22/2018
Modify/Update this entry
|Visitors||Authors||More about us||Links|
Search, Browse the Repository
Give us feedback
|Optimization Journals, Sites, Societies|