Sinkhorn Distributionally Robust Optimization [article]

Jie Wang, Rui Gao, Yao Xie
2021 arXiv   pre-print
We study distributionally robust optimization with Sinkorn distance -- a variant of Wasserstein distance based on entropic regularization. We derive convex programming dual reformulations when the nominal distribution is an empirical distribution and a general distribution, respectively. Compared with Wasserstein DRO, it is computationally tractable for a larger class of loss functions, and its worst-case distribution is more reasonable. To solve the dual reformulation, we propose an efficient
more » ... atch gradient descent with a bisection search algorithm. Finally, we provide various numerical examples using both synthetic and real data to demonstrate its competitive performance.
arXiv:2109.11926v1 fatcat:lcwrltfisjbyznk3743vxhcsme