Dr. Belkin’s research focuses on designing and analyzing practical algorithms for machine learning based on non-linear structure of high dimensional data, in particular manifold and spectral methods. He is also interested in a range of theoretical questions concerning the computational and statistical limits of learning and in the mathematical foundations of learning structure from data.
PhD, Mathematics, University of Chicago
MSc, Mathematics, University of Chicago
HonBSc with High Distinction, Mathematics, University of Toronto