OCLGMLSep 24, 2021

Sinkhorn Distributionally Robust Optimization

arXiv:2109.11926v555 citations
Originality Incremental advance
AI Analysis

This work addresses robust optimization under distributional uncertainty for applications in machine learning and operations research, representing an incremental improvement with a focus on computational efficiency.

The paper tackles distributionally robust optimization using Sinkhorn distance by deriving a convex dual reformulation and developing a stochastic mirror descent algorithm with computational guarantees, demonstrating superior performance in numerical examples.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes