Sinkhorn Distributionally Robust Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Jie, Gao, Rui, Xie, Yao
Format: Preprint
Published: 2021
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915213336379392
author Wang, Jie
Gao, Rui
Xie, Yao
author_facet Wang, Jie
Gao, Rui
Xie, Yao
contents We study distributionally robust optimization with Sinkhorn distance -- a variant of Wasserstein distance based on entropic regularization. We derive a convex programming dual reformulation for general nominal distributions, transport costs, and loss functions. To solve the dual reformulation, we develop a stochastic mirror descent algorithm with biased subgradient estimators and derive its computational complexity guarantees. Finally, we provide numerical examples using synthetic and real data to demonstrate its superior performance.
format Preprint
id arxiv_https___arxiv_org_abs_2109_11926
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Sinkhorn Distributionally Robust Optimization
Wang, Jie
Gao, Rui
Xie, Yao
Optimization and Control
Machine Learning
We study distributionally robust optimization with Sinkhorn distance -- a variant of Wasserstein distance based on entropic regularization. We derive a convex programming dual reformulation for general nominal distributions, transport costs, and loss functions. To solve the dual reformulation, we develop a stochastic mirror descent algorithm with biased subgradient estimators and derive its computational complexity guarantees. Finally, we provide numerical examples using synthetic and real data to demonstrate its superior performance.
title Sinkhorn Distributionally Robust Optimization
topic Optimization and Control
Machine Learning
url https://arxiv.org/abs/2109.11926