BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Monday Seminar - An ALPS’ view of Sparse Recovery
DTSTART:20101122T161500
DTSTAMP:20260427T223641Z
UID:66df82ed37fa2483cf016148bbaba9466d9b03cc5651b7b0336c4ada
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Volkan Cevher\, Laboratory for Information and Inference
  Systems\, EPFL\, invited by Prof. Willy Zwaenepoel\nAbstract : Compressiv
 e sensing (CS) is an alternative to Shannon/Nyquist sampling for acquisiti
 on of sparse or compressible signals that can be well approximated by just
  a few (“sparse”) coefficients in a basis. Instead of taking periodic 
 samples\, we measure inner products with random vectors and then recover t
 he signal via a sparsity-seeking optimization or greedy algorithm. The sta
 ndard CS theory dictates that robust recovery is possible from a number of
  measurements that is commensurate with the sparsity level of signals. The
  implications are promising for many applications and enable the design of
  new kinds of analog-to-digital converters\, cameras and imaging systems\,
  and sensor networks.\n \nIn this talk\, we introduce three first-order\, 
 iterative CS recovery algorithms\, collectively dubbed algebraic pursuits 
 (ALPS)\, and derive their theoretical convergence and estimation guarantee
 s. We empirically demonstrate that ALPS outperforms the Donoho-Tanner phas
 e transition bounds for sparse recovery using Gaussian\, Fourier\, and spa
 rse measurement matrices. We then describe how to use ALPS for CS recovery
  in redundant dictionaries. Finally\, we discuss how ALPS can also incorpo
 rate union-of-subspaces-based sparsity models in recovery with provable gu
 arantees to make CS better\, stronger\, and faster.\n\nBio : Dr. Volkan Ce
 vher received his BSc degree (valedictorian) in Electrical Engineering fro
 m Bilkent University in 1999\, and his PhD degree in Electrical and Comput
 er Engineering from Georgia Institute of Technology in 2005. He held Resea
 rch Scientist positions at University of Maryland\, College Park during 20
 06-2007 and at Rice University during 2008-2009. Currently\, he is an Assi
 stant Professor at Ecole Polytechnique Federale de Lausanne with joint app
 ointment at the Idiap Research Institute and a Faculty Fellow at Rice Univ
 ersity. His research interests include signal processing theory\, machine 
 learning and graphical models and information theory. 
LOCATION:INM202
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR