CCM Colloquium: Anna Gilbert (Yale University)

Title: Metric representations: Algorithms and Geometry

Abstract: Given a set of distances amongst points, determining what metric representation is most “consistent” with the input distances or the metric that best captures the relevant geometric features of the data is a key step in many machine learning algorithms. In this talk, we discuss a number of variants of this problem, from convex optimization problems with metric constraints to sparse metric repair.