Coresets for Wasserstein Distributionally Robust Optimization Problems

10/09/2022
by   Ruomin Huang, et al.
0

Wasserstein distributionally robust optimization () is a popular model to enhance the robustness of machine learning with ambiguous data. However, the complexity of can be prohibitive in practice since solving its “minimax” formulation requires a great amount of computation. Recently, several fast training algorithms for some specific machine learning tasks (e.g., logistic regression) have been developed. However, the research on designing efficient algorithms for general large-scale s is still quite limited, to the best of our knowledge. Coreset is an important tool for compressing large dataset, and thus it has been widely applied to reduce the computational complexities for many optimization problems. In this paper, we introduce a unified framework to construct the ϵ-coreset for the general problems. Though it is challenging to obtain a conventional coreset for due to the uncertainty issue of ambiguous data, we show that we can compute a “dual coreset” by using the strong duality property of . Also, the error introduced by the dual coreset can be theoretically guaranteed for the original objective. To construct the dual coreset, we propose a novel grid sampling approach that is particularly suitable for the dual formulation of . Finally, we implement our coreset approach and illustrate its effectiveness for several problems in the experiments.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/09/2015

A Smoothed Dual Approach for Variational Wasserstein Problems

Variational problems that involve Wasserstein distances have been recent...
research
06/30/2021

Robust Coreset for Continuous-and-Bounded Learning (with Outliers)

In this big data era, we often confront large-scale data in many machine...
research
06/20/2014

Playing with Duality: An Overview of Recent Primal-Dual Approaches for Solving Large-Scale Optimization Problems

Optimization methods are at the core of many problems in signal/image pr...
research
11/13/2018

Semi-dual Regularized Optimal Transport

Variational problems that involve Wasserstein distances and more general...
research
02/27/2020

Layered Sampling for Robust Optimization Problems

In real world, our datasets often contain outliers. Moreover, the outlie...
research
10/28/2019

A First-Order Algorithmic Framework for Wasserstein Distributionally Robust Logistic Regression

Wasserstein distance-based distributionally robust optimization (DRO) ha...
research
05/11/2021

Frank-Wolfe Methods in Probability Space

We introduce a new class of Frank-Wolfe algorithms for minimizing differ...

Please sign up or login with your details

Forgot password? Click here to reset