Title: Generalized maximum entropy estimation
Speaker: Dr David Sutter
Affiliation: Institute for Theoretical Physics, ETH Zurich
Location: 217 Huxley Building
Time: 14:00 – 15:00

Abstract. We consider the problem of estimating a probability distribution that maximizes the entropy while satisfying a finite number of moment constraints, possibly corrupted by noise. Based on duality of convex programming, we present a novel approximation scheme using a smoothed fast gradient method that is equipped with explicit bounds on the approximation error.

This is joint work with T. Sutter, P. Esfahani, and J. Lygeros (arXiv:1708.07311).

Biography. Dr David Sutter is a postdoctoral researcher at ETH Zurich, working on mathematical aspects of quantum information theory. He obtained his PhD degree from the Institute for Theoretical Physics at ETH Zurich under the supervision of Prof. Renato Renner. Dr Sutter’s interests lie in the intersection of quantum mechanics, information theory, and mathematical physics. To understand the fundamental limits of information processing and communications, he utilizes tools from matrix analysis, optimization theory and probability theory.