Determinantal Point Processes and Some Matrix Recovery Problems

Start: 04/10/2018 - 4:15pm
End  : 04/10/2018 - 5:30pm


John Urschel (Doctoral Candidate MIT)


Determinantal Point Processes (DPPs) are a family of probabilistic models that have a repulsive behavior, and lend themselves naturally to many tasks in machine learning where returning a diverse set of objects is important. We will explore the problem of learning the parameters of a DPP and study some related matrix recovery problems.

John C. Argue Auditorium, Millikan 1051, Pomona College

Misc. Information

John Urschel, graduated from Penn State in 2013 with an MA in Topics in Applied Mathematics.  In 2014 he was drafted by the Baltimore Ravens, where he played professional football for three years.  While playing pro ball he was accepted into the MIT doctoral program in applied mathematics.  In 2017 he retired from football to focus on his graduate studies.  He has done research in number of areas, including combinatorial optimization, computational finance, graph theory, machine learning, mathematical physics, numerical PDEs, and others.  He has 11 peer-reviewed publications in mathematics and has the fastest eigensolver for minimal Laplacian eigenvectors.  Currently he spends most of his time thinking about graph theory, machine learning, and numerical analysis.

Claremont Graduate University | Claremont McKenna | Harvey Mudd | Pitzer | Pomona | Scripps
Proudly Serving Math Community at the Claremont Colleges Since 2007
Copyright © 2018 Claremont Center for the Mathematical Sciences