May 12, 2015, 4pm
Sebastien Bubeck, Microsoft Research, Redmond.
The Entropic Barrier: A New and Optimal Universal Self-concordant Barrier
Abstract: A fundamental result in the theory of Interior Point Methods is Nesterov and Nemirovski’s construction of a universal self-concordant barrier. In this talk I will introduce the entropic barrier, a new (and in some sense optimal) universal self-concordant barrier. The entropic barrier connects many topics of interest in Machine Learning: exponential families, convex duality, log-concave distributions, Mirror Descent, and exponential weights.