Learning functions on the space of persistence diagrams

Speaker:  Jose Perea (Michigan State University)

Speaker's URL:  https://www.joperea.com/

Abstract:  The persistence diagram is an increasingly useful shape descriptor from Topological Data Analysis, but its use alongside typical machine learning techniques requires mathematical finesse. We will describe in this talk a mathematical framework addressing the problem of approximating continuous functions on compact subsets of the space of persistence diagrams. We will also show how these techniques can be applied to problems in semi-supervised learning where these descriptors are relevant.

URL associated with Seminar:  https://tgda.osu.edu/activities/tdga-seminar/