BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Data science and the curse of phase transitions
DTSTART:20161010T161500
DTEND:20161010T171500
DTSTAMP:20260609T230503Z
UID:175a5d233acf459e89f2845958ec73130ebb6d29579b5524af81e39d
CATEGORIES:Conferences - Seminars
DESCRIPTION:Prof. Marc Mézard\, Ecole normale supérieure - PSL Research 
 university\, Paris\nExtracting information\, and more generally extracting
  knowledge from large datasets is arguably one of the main frontiers of mo
 dern science\, common to a broad variety of disciplines. Bayesian approach
 es to machine learning and signal processing provide a conceptual framewor
 k in which information bits interact through constraints (due to prior kno
 wledge or to measurements). Statistical physics has helped to develop new 
 approaches and very powerful algorithms in this context\, where collective
  phenomena\, like phase transitions and the occurrence of glassy phases\, 
 play a major role. This talk will review some of the main developments in 
 this field\, illustrated by specific examples like compressed sensing.
LOCATION:Auditoire CE3 http://plan.epfl.ch/?zoom=20&recenter_y=5864182.970
 7&recenter_x=731341.22227&layerNodes=fonds\,batiments\,labels\,information
 \,parkings_publics\,arrets_metro\,transports_publics&floor=1&q=ce3
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR