BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VTIMEZONE
TZID:Europe/Vienna
BEGIN:DAYLIGHT
DTSTART:20210328T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20201025T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260403T220426Z
UID:1607958000@ist.ac.at
DTSTART:20201214T160000
DTEND:20201214T170000
DESCRIPTION:Speaker: Elchanan Mossel\nhosted by Uli Wagner\nAbstract: There
  is a very simple algorithm for the inference on trees. This algorithm\, 
 known as Belief Propagation" is widely used in coding theory\, machine lea
 rning\, and evolutionary inference\, among many other areas. The talk wil
 l be devoted to deep connections between different aspects of this algorit
 hm and its applications in different areas. We will highlight the interpl
 ay between Belief Propagation\, linear estimators (statistics)\, the Keste
 n-Stigum bound (probability)\, and Replica Symmetry Breaking (statistical
  physics). We will discuss the role of Belief Propagation in proving phas
 e transitions for phylogenetic reconstruction in evolutionary biology and 
 in optimal algorithms for inference of block models in statistics and mac
 hine learning. Finally\, we will discuss the computational complexity of t
 his simple" algorithm. 
LOCATION:Online on Zoom\, ISTA
ORGANIZER:eventoffice@ist.ac.at
SUMMARY:Elchanan Mossel: Belief-propagation\, evolutionary inference\, phas
 e transitions\, and complexity 
URL:https://talks-calendar.ista.ac.at/events/2705
END:VEVENT
END:VCALENDAR
