BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Statistical estimation in high dimensions:  Rigorous results for n
 onconvex optimization
DTSTART:20151105T171500
DTEND:20151105T180000
DTSTAMP:20260406T211432Z
UID:ecc1a7160fc8ef2bf0765751d73a050ec31a5faefad4db3be31bf919
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Martin Wainwright\, Berkeley University\nThe classical c
 omplexity barrier in continuous optimization is between convex (solvable i
 n polynomial time) and nonconvex (intractable in the worst-case setting). 
 However\, many problems of interest are not constructed adversarially\, bu
 t instead arise from probabilistic models of scientific phenomena.  Can w
 e provide rigorous guarantees for such random ensembles of nonconvex optim
 ization problems? \nIn this talk\, we survey various positive answers to 
 this question\, including optimal results for sparse regression with nonco
 nvex penalties\, and direct approaches to low-rank matrix recovery.  All 
 of these results involve natural weakenings of convexity that hold for var
 ious classes of nonconvex functions\, thus shifting the barrier between t
 ractable and intractable.Biography :\nMartin Wainwright joined the faculty
  at University of California at Berkeley in Fall 2004\, and is currently a
  Professor with a joint appointment between the Department of Statistics a
 nd the Department of Electrical Engineering and Computer Sciences. He rece
 ived his Bachelor's degree in Mathematics from University of Waterloo\, Ca
 nada\, and his Ph.D. degree in Electrical Engineering and Computer Science
  (EECS) from Massachusetts Institute of Technology (MIT)\, for which he wa
 s awarded the George M. Sprowls Prize from the MIT EECS department in 2002
 . He is interested in high-dimensional statistics\, information theory and
  statistics\, and statistical machine learning. He has received an Alfred 
 P. Sloan Foundation Research Fellowship (2005)\, IEEE Best Paper Awards fr
 om the Signal Processing Society (2008) and Communications Society (2010)\
 ; the Joint Paper Award from IEEE Information Theory and Communication Soc
 ieties (2012)\; a Medallion Lecturer (2013) of the Institute for Mathemati
 cal Statistics\; a Section Lecturer at the International Congress of Mathe
 maticians (2014)\; and the COPSS Presidents' Award in Statistics (2014). H
 e is currently serving as an Associate Editor for the Annals of Statistics
 \, Journal of Machine Learning Research\, Journal of the American Statisti
 cal Association\, and Journal of Information and Inference.
LOCATION:CM 1 5 https://plan.epfl.ch/?room==CM%201%205
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR