[Ml-stat-talks] Princeton Optimization Seminar: Sebastien Bubeck, TODAY, 4:30PM
Amir Ali Ahmadi
a_a_a at princeton.edu
Tue Feb 17 09:35:46 EST 2015
----- Princeton Optimization Seminar -----
DATE: Tuesday, February 17, 2015
LOCATION: Sherrerd Hall room 101
SPEAKER: Sebastien Bubeck, Princeton/Microsoft
TITLE: The entropic barrier: a simple and optimal universal self-concordant barrier
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.
Sebastien Bubeck is an assistant professor in ORFE at Princeton University, and a researcher in the Theory Group at Microsoft Research, Redmond.
=== Princeton Optimization Seminar ===
If you would like to subscribe to the mailing list of the optimization seminar series, please visit the link below or send an email with
SUBSCRIBE opt-seminar in the body to listserv at lists.princeton.edu<mailto:listserv at lists.princeton.edu>.
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the Ml-stat-talks