Title:

Cost Learning via Inverse Optimal Transport

Abstract:

We propose a unified data-driven framework based on inverse optimal transport that can learn adaptive, nonlinear interaction cost function from noisy and incomplete empirical matching matrix and predict new matching in various matching contexts. We emphasize that the discrete optimal transport plays the role of a variational principle which gives rise to an optimization-based framework for modeling the observed empirical matching data. Our formulation leads to a bi-level non-convex optimization problem, for which we develop an efficient algorithm based on a saddle-point formulation of the optimization problem. The proposed approach has wide applicability including predicting matching in online dating, labor market, college application, and crowdsourcing. We back up our claims with numerical experiments on both synthetic data and real-world data sets.

Biography:

Dr. Xiaojing Ye is an associate professor at the Department of Mathematics and Statistics in Georgia State University, Atlanta, USA. Prior to joining Georgia State University in 2013, Dr. Ye was a visiting assistant professor at the School of Mathematics in Georgia Institute of Technology, USA. Dr. Ye received his doctoral degree in mathematics and master's degree in statistics from the University of Florida, USA in 2011 and 2009 respectively, and the bachelor’s degree in mathematics from Peking University in 2006. His research focuses on applied and computational mathematics, particularly PDE-based image analysis, numerical optimization, analysis and computational methods in machine learning.