Princeton University

School of Engineering & Applied Science

Entropy, geometry, and a CLT for Wishart matrices

Sebastien Bubeck,Theory Group at Microsoft Research
E-Quad, B205
Wednesday, October 7, 2015 - 10:45am

Abstract: Wishart matrices appear in many areas of (applied) mathematics, e.g. as covariance matrices in statistics, or as a model of a random mixed quantum state in physics. In this talk I will prove a new central limit theorem for high-dimensional Wishart matrices, using a now well-understood information theoretic machinery (which will be reviewed). I will discuss an application of this result to the problem of finding geometry in random networks. Several (new) conjectures will be mentioned too.
Joint work with Shirshendu Ganguly.
Bio: Sebastien Bubeck is a researcher in the Theory Group at Microsoft Research. Prior to MSR he was an assistant professor in the ORFE department at Princeton University. His research has won a few awards, including the 2010 Jacques Neveu prize (best French Ph.D. in probability/statistics) and a 2015 Sloan Fellowship in Computer Science.