BEGIN:VCALENDAR
VERSION:2.0
CALSCALE:GREGORIAN
PRODID:UW-Madison-Physics-Events
BEGIN:VEVENT
SEQUENCE:1
UID:UW-Physics-Event-4666
DTSTART:20171114T180500Z
DTEND:20171114T190000Z
DTSTAMP:20260419T021645Z
LAST-MODIFIED:20171012T134230Z
LOCATION:4274 Chamberlin (refreshments will be served)
SUMMARY:Inference for high-dimensional self-exciting point processes\,
  Chaos & Complex Systems Seminar\, Becca Willett\, UW Department of El
 ectrical and Computer Engineering
DESCRIPTION:In a variety of settings\, our only glimpse at a networkâ€
 ™s structure is through observations of a corresponding dynamical syst
 em. For instance\, in a social network\, we may observe a time series 
 of members’ activities\, such as posts on social media. In biologica
 l neural networks\, firing neurons can trigger or inhibit the firing o
 f their neighbors\, so that information about the network structure is
  embedded within spike train observations. These processes are “self
 -exciting” in that the likelihood of future events depends on past e
 vents. In these and other settings\, a network’s structure correspon
 ds to the extent to which one node’s activity stimulates or inhibits
  activity in another node. In this talk\, I will describe sparsity-reg
 ularized inference methods and theoretical guarantees that reflect the
  role of the network’s degree distribution and other network propert
 ies in determining the complexity of the inference problem for large-s
 cale networks. In addition\, we will see how these techniques can be u
 sed in applications ranging from criminology to predicting adverse dru
 g reactions.
URL:https://www.physics.wisc.edu/events/?id=4666
END:VEVENT
END:VCALENDAR