BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Compressed Sensing of Big Data Networks
DTSTART:20171220T100000
DTEND:20171220T120000
DTSTAMP:20260414T221446Z
UID:fae4dee6c0f9e517a1af9b3ca7da723f347546dfbf2ad3f594075e9f
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Alexander Jung\, Aalto University\nBio: Alexander Jung r
 eceived the Diplom-Ingenieur (equivalent to MSc) and Dr. techn. (equivalen
 t to Phd) degrees in electrical engineering/signal processing from Technic
 al University Wien\, Vienna\, Austria in 2008 and 2012\, respectively. Bet
 ween 2012 and 2015 he held Post-Doc positions at ETH Zurich and TU Wien. I
 n 2015 he has been appointed Assitant Professor for Machine Learning at Aa
 lto University\, Espoo\, Finland. He has received numerous national and in
 ternational awards\, including a best student paper award at the conferenc
 e IEEE ICASSP 2011 and the "Promotio sub auspiciis Praesidentis rei public
 ae" (highest academic distinction achievable in Austria).\n\nHis current r
 esearch revolves around fundamental limits of and efficient algorithms for
  machine learning based on massive network-structured datasets (big data o
 ver networks). He is co-editor of the special research topic "Compressed S
 ensing over Complex Networks for Learning from Big Data over Networks" wit
 hin Frontiers in Applied Mathematics and Statistics.\nIn this talk\, we di
 scuss our recent work on developing a theory of compressed sensing for gra
 ph signals defined over complex networks. These graph signals represent th
 e label information contained in massive network-structured datasets (big 
 data over networks). By drawing on compressed sensing for ordinary sparse 
 signals\, we have introduced the network nullspace property (NNSP) and the
  network compatibility condition (NCC)\, which guarantee that certain conv
 ex learning methods\, including the recently proposed network Lasso\, accu
 rately learn clustered graph signals from a small number of signal samples
 . These conditions involvethe connectivity structure of the underlying net
 work via requiring the existence of certain network flows.
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR