BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium : Leveraging inexactness for scalability
DTSTART:20130415T161500
DTEND:20130415T173000
DTSTAMP:20260601T194237Z
UID:9456e5a2e8ee3c94a4c41778ff2456d1a4062453cf1c36370fe6cb91
CATEGORIES:Conferences - Seminars
DESCRIPTION:Suvrit Sra\, Max Planck Institute for Intelligent Systems\nIC 
 faculty candidate\nAbstract\nMankind generates data at a pace that vastly 
 outstrips processing power\, so much so that even "tractable" algorithms m
 ay be too slow. Linear\, or better yet\, sublinear complexity is the most 
 we can afford.  These limitations induce a paradigm shift in modern data 
 analysis is approached: lower accuracy\, randomization\, online processing
 \, distributed computation\, inexact methods and inexact models gain the c
 enterstage.\nIn my talk\, I illustrate these views by culling a few exampl
 es from my own research. I mention not only progress on key components for
  large-scale optimization\, but also two main items from recent work. The 
 first is a new framework for inexact optimization\, which subsumes a slew 
 of known large-scale algorithms\; it is also the first of its kind for sca
 lably tackling nonconvex\, nonsmooth problems that pervade data driven res
 earch. The second is an unexpected instance of inexactness: we replace a d
 ifficult convex model with an easier nonconvex one\, which amazingly can s
 till be solved to global optimality. I will also briefly mention broader c
 onnections of our model to areas within mathematics and information theory
 . To add perspective\, I ground the whole talk in applications from comput
 er vision\, image processing\, and machine learning that have driven my th
 eoretical and algorithmic work.Biography\nSuvrit Sra is a Sr. Research Sci
 entist at the Max Planck Institute for Intelligent Systems in Tübingen\, 
 Germany. He obtained Ph.D. in Computer Science from the University of Texa
 s at Austin in 2007. In Spring 2013 he is visiting UC Berkeley and teachin
 g a graduate course on convex optimization. His research focuses on "large
 -scale data analysis and optimization"\; in particular\, he designs\, anal
 yzes\, and implements algorithms for data intensive problems in scientific
  computing\, statistics\, computer vision\, and machine learning. His math
 ematical interests span a variety of areas including matrix analysis\, non
 commutative algebra\, and geometry.\nHis research has won awards at severa
 l international venues\; the most recent being the "SIAM Outstanding Paper
  Prize (2011)" for his work on metric nearness. He regularly organizes the
  Neural Information Processing Systems (NIPS) workshops on "Optimization f
 or Machine Learning"\, and and has recently co-edited a book with the same
  title (MIT Press\, 2011).
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR