Online Program Home
My Program

Abstract Details

Activity Number: 387 - Foundations of Data Science
Type: Invited
Date/Time: Tuesday, July 31, 2018 : 2:00 PM to 3:50 PM
Sponsor: IMS
Abstract #326524
Title: A Statistical View on Optimal Transport: Inference, Algorithms, Applications
Author(s): Axel Munk* and Joern Schrieber and Max Sommerfeld and Carla Tameling
Companies: University of Goettingen and Department for Mathematics and Computer Science and Department for Mathematics and Computer Science and Department for Mathematics and Computer Science
Keywords: Wasserstein metric; sensitivity analysis; linear program; nansocale imaging; large scale inference; bootstrap
Abstract:

The Wasserstein distance (WD), also known as Monge-Kantorovich-Rubinstein distance in the physical sciences, earth-mover's distance in computer science or optimal transport distance in optimization, is one of the most fundamental metrics on probability measures. It has perceived great interest recently in many applications ranging from computer vision to genetics as it measures the amount of 'work' required to transform one probability distribution into another.

In this talk we provide a statistical perspective on the WD estimated from data. We derive distributional limits for probability measures supported on countable sets. Our approach is based on sensitivity analysis of optimal values of infinite dimensional mathematical programs and a delta method for non-linear derivatives. We give an explicit form of the limiting distribution for ultra-metric spaces, e.g. rooted trees. Deviation bounds and bootstrap schemes will be discussed which offer tools for optimal transport based inference for large scale problems. Applications from nanoscale cell imaging and classification are given.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2018 program