BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:LearnIng\, Optimization\, and DecisioN Systems (LIONS)
DTSTART:20180419T171500
DTSTAMP:20260407T105815Z
UID:ffb9920d38b85adfbdec353aff5ee2089d9717650c9426a6f151d817
CATEGORIES:Inaugural lectures - Honorary Lecture
DESCRIPTION:Prof. Volkan Cevher\, IEL (EPFL)\nMassive data poses a fundame
 ntal challenge to learning algorithms\, which is captured by the following
  computational dogma: the running time of an algorithm increases with the 
 size of its input data. The available computational power\, however\, is g
 rowing slowly relative to data sizes. Hence\, large-scale machine learning
  problems of interest require increasingly more time to solve.\n\nOur rese
 arch demonstrates that this dogma is false in general\, and supports an em
 erging perspective in computation: data should be treated as a resource th
 at can be traded off with other resources\, such as running time. For data
  acquisition and communications\, we have also shown related sampling\, en
 ergy\, and circuit area trade-offs.\n\nThis talk will summarize our work c
 onfronting these challenges by building on the new mathematical foundation
 s on how we generate data via sampling\, how we set up learning objectives
  that govern our fundamental goals\, and how we optimize these goals to ob
 tain solutions and to make optimal decisions. We then demonstrate task-spe
 cific\, end-to-end trade-offs (e.g.\, samples\, power\, computation\, stor
 age\, and statistical precision) in broad domains\, by not only with our r
 ecently built\, low-power analog-to-information conversion hardware for ne
 ural signal acquisition\, but also accelerating magnetic resonance imaging
 \, and engineering new decision tools for discovery in machine learning.\n
  \nProgram\n\n-Introduction by Giovanni de Micheli\, Director of the Inst
 itute of Electrical Engineering and of the Centre of Integrated Systems\n-
 Inaugural lecture of Prof. Volkan Cevher\, "LearnIng\, Optimization\, and 
 DecisioN Systems (LIONS)"\n\nRegistration is required: http://go.epfl.ch/c
 evher\n\nBio:\nVolkan Cevher received the B.Sc. (valedictorian) in electri
 cal engineering from Bilkent University in Ankara\, Turkey\, in 1999 and t
 he Ph.D. in electrical and computer engineering from the Georgia Institute
  of Technology in Atlanta\, GA in 2005. He was a Research Scientist with t
 he University of Maryland\, College Park from 2006-2007 and also with Rice
  University in Houston\, TX\, from 2008-2009. Currently\, he is an Associa
 te Professor at the Swiss Federal Institute of Technology Lausanne and a F
 aculty Fellow in the Electrical and Computer Engineering Department at Ric
 e University. His research interests include signal processing theory\, ma
 chine learning\, convex optimization\, and information theory. Dr. Cevher 
 was the recipient of the IEEE Signal Processing Society Best Paper Award i
 n 2016\, a Best Paper Award at CAMSAP in 2015\, a Best Paper Award at SPAR
 S in 2009\, and an ERC CG in 2016 as well as an ERC StG in 2011.
LOCATION:ELA1 http://plan.epfl.ch/?lang=fr&room=ELA1
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR