Preprint
Jul 2026
Distributionally Robust Optimization via Targeted Integral Probability Metrics for General Data Processes
This work derives exact infinite-dimensional dual reformulations, establishes out-of-sample and excess-risk guarantees, and develops a conservative Monte Carlo approximation scheme with convergence and suboptimality guarantees for piecewise affine losses.
L. Fang, Jianqiang Cheng, G. A. Hanasusanto et al.
· 0 citations