Tuesday, September 13, 2016 - 4:00pm to Wednesday, September 14, 2016 - 3:55pm
Event Calendar Category
LIDS Seminar Series
Speaker Name
Suvrit Sra
Affiliation
MIT
Building and Room Number
32-141
Abstract
In this talk, I will highlight some aspects of geometry and its role in optimization. In particular, I will talk about optimization problems whose parameters are constrained to lie on a manifold or in a suitable metric space. These geometric constraints on the parameters make the problems numerically challenging, which motivates us to take a closer look at geometry for obtaining better algorithms and for gaining a richer theoretical understanding.
We'll make our foray into geometric optimization via geodesic convexity, a concept that generalizes the notion of (usual linear space) convexity to nonlinear metric spaces (e.g., Riemannian manifolds). I will outline some of our results that contribute to g-convex analysis as well as to the complexity theory of first-order g-convex optimization. I will mention a few very interesting optimization problems where g-convexity proves to be useful. In closing, I will mention recent extensions beyond g-convex geometric optimization along with important open problems.
Biography
Suvrit Sra is a Principal Research Scientist (Research Faculty) at the Laboratory for Information and Decision Systems (LIDS) at Massachusetts Institute of Technology (MIT). He obtained his PhD in Computer Science from the University of Texas at Austin in 2007. Before moving to MIT, he was a Senior Research Scientist at the Max Planck Institute for Intelligent Systems, in Tübingen, Germany. He has also held visiting faculty positions at UC Berkeley (EECS) and Carnegie Mellon University (Machine Learning Department) during 2013-2014.
His research is dedicated to bridging a number of mathematical areas such as metric geometry, matrix analysis, convex analysis, probability theory, and optimization with machine learning. More broadly, he is interested in algorithmically oriented topics within engineering, science, and healthcare. His work has won several awards at machine learning venues, as well as the 2011 "SIAM Outstanding Paper" award. He has co-chaired OPT2008-2016, NIPS workshops on "Optimization for Machine Learning;" he has also edited a book with the same title (MIT Press, 2011).