BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//talks.cam.ac.uk//v3//EN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:Isaac Newton Institute Seminar Series
SUMMARY:Random walk models of networks: modeling and infer
ring complex dependence - Benjamin Bloem-Reddy (Co
lumbia University)
DTSTART;TZID=Europe/London:20160727T113000
DTEND;TZID=Europe/London:20160727T120000
UID:TALK66858AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/66858
DESCRIPTION:A signature of many network datasets is strong loc
al dependence\, a \;phenomenon that \;give
s rise to frequently observed properties such as t
ransitive triples\, pendants\, and structural hete
rogeneity. One difficulty in modeling such depende
nce is that the notion of locality may not be well
-defined\, and it is likely to be heterogeneous th
roughout the network. Furthermore\, models that do
not assume some form of conditional independence
on the edges typically are intractable or too simp
listic to serve as useful statistical models. We i
ntroduce a class of models\, based on random walks
\, that allows the scale of dependence to vary\; i
t is able to generate a range of network structure
s faithful to those observed in real data\, and it
admits tractable inference procedures.
Thi
s is joint work with Peter Orbanz.
LOCATION:Seminar Room 1\, Newton Institute
CONTACT:INI IT
END:VEVENT
END:VCALENDAR