Graph methods for semi-supervised learning and Bayesian inverse problems

Computational and Applied Mathematics Colloquium

Meeting Details

For more information about this meeting, contact Kristin Berrigan, John Harlim.

Speaker: Daniel Sanz-Alonso, University of Chicago

Abstract: In this talk I will consider two graph-based learning problems. The first one concerns a graph formulation of Bayesian semi-supervised learning, and the second one concerns kernel discretization of Bayesian inverse problems in manifolds. I will show that understanding the continuum limit of these graph-based learning problems is helpful in designing sampling algorithms whose rate of convergence does not deteriorate in the limit of large number of graph nodes.


Room Reservation Information

Room Number: 114 McAllister

Date: 09/16/2019

Time: 12:20pm - 1:30pm