Data Science Faculty Candidate talk - "Learning Interaction Laws in Systems of Agents From Trajectory Data" by Dr. Sui Tang

Thursday, January 24, 2019
11:00 am to 12:00 pm


Floor/Room #: 

Dr. Sui Tang
Data Science Faculty Candidate
Title: Learning Interaction Laws In Systems Of Agents From Trajectory Data.
Systems of interacting agents arise in many areas of science, such as particle systems in physics, opinion dynamics in social science and flocking and swarming models in biology. Inferring the laws of interaction of agents from observational data is a fundamental challenge in a wide variety of disciplines. We propose a non-parametric statistical learning approach to estimate the governing laws of distance-based interactions, with no reference or assumption about their analytical form, from data consisting trajectories of interacting agents. We present efficient regression algorithms to learn the interaction kernel and develop a learning theory addressing consistency and optimal learning rate of the estimators. Especially, we show that despite the high-dimensionality of the systems, optimal learning rates can still be achieved, equal ot that of a one-dimensional regression problem. We demonstrate the efficiency of the algorithms on various  examples. Finally, I will conclude with some open questions and future research directions.

Dr Sui Tang is currently an Assistant Research Professor in the Department of Mathematics at Johns Hopkins University. She earned her Ph.D. in mathematics at Vanderbilt University, in 2016. Her research interests are in statistical learning, high-dimensional data analysis, and applied and computational harmonic analysis.