• Speaker: Volkan Cevher, Swiss Federal Institute of Technology Lausanne
• Time: December 2, 2013, 3:30pm-5:00pm
• Location: POB 6.304
• Host: Inderjit S. Dhillon

Talk Abstract

We propose a variable metric framework for minimizing the sum of a self-concordant function and a possibly non-smooth convex function endowed with a computable proximal operator. We theoretically establish the convergence of our framework without relying on the usual Lipschitz gradient assumption on the smooth part. An important highlight of our work is a new set of analytic step-size selection and correction procedures based on the structure of the problem. We describe concrete algorithmic instances of our framework for several interesting large-scale applications and demonstrate them numerically on both synthetic and real data.

Speaker Bio

Volkan Cevher received a B.Sc. (valedictorian) in Electrical Engineering in 1999 from Bilkent University in Ankara, Turkey, and he received a Ph.D. in Electrical and Computer Engineering in 2005 from the Georgia Institute of Technology in Atlanta, GA. He held research scientist positions at the University of Maryland, College Park from 2006–2007 and at Rice University in Houston, TX, from 2008–2009. Currently, he is an Assistant Professor at the Swiss Federal Institute of Technology Lausanne and a Faculty Fellow in the Electrical and Computer Engineering Department at Rice University. His research interests include signal processing theory, machine learning, graphical models, and information theory. Dr. Cevher received a Best Paper Award at SPARS in 2009 and an ERC StG in 2011.