Optimal transport and signal processing
Directed by Drs Shuchin Aeron and James Murphy
Description: Optimal transport is the study of the geometry of the space of probability measures. Recent computational advances have allowed it to impact a wide range of applications including image processing, machine learning, and statistics. We will focus on the development of novel methods for change point and anomaly detection via optimal transport. A focus will be on applications to time series analysis and high-dimensional remotely sensed images. Students can expect to learn about optimization, probability theory, statistical learning, and numerical experimentation. Students interested in this project should have a background in real analysis, probability, and statistics, and have some coding experience.