Title:
The Cumulative Distribution Transform for Data Analysis and Machine Learning
Abstract:
Optimal transport methods have gathered increased interest from the mathematics and engineering communities. In many situations ranging from machine learning and signal processing, transport-based algorithms have outperformed state of the art methods. In this talk, we will describe the Cumulative Distribution Transform (CDT), its connections to the Monge and Kantorovich problems, and its relation to the Wasserstein metrics. Properties of the CDT will be discussed, including classes of problems for which the CDT is advantageous.
|