BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Robust Spatial Temporal Forecasting - Ayan Mukhopadhyay\, Stanford
  University
DTSTART:20200630T100000Z
DTEND:20200630T113000Z
UID:TALK148537@talks.cam.ac.uk
CONTACT:Jonathan Rosser
DESCRIPTION:Abstract -- Spatio-temporal criminal incident prediction is am
 ong the central issues in law enforcement\, with applications ranging from
  predicting assaults and terrorist acts to predicting poaching. However\, 
 state of the art approaches fail to account for criminal evasion\, a commo
 n form of which is spatial shift in crime. This is a major problem in doma
 ins like forests\, where poachers shift their area of interest based on pa
 trols. This talk will present a novel and general optimization framework b
 ased on Stackelberg games for incident forecasting that is robust to such 
 spatial shifts\, and discuss algorithmic methodologies of solving the resu
 lting problem. Speaker-bio – Ayan Mukhopadhyay is a Post-Doctoral Resear
 ch Fellow at the Stanford Intelligent Systems Lab at Stanford University\,
  USA. His research interests include multi-agent systems\, robust machine 
 learning and decision-making under uncertainty. He was awarded the 2019 CA
 RS Post-doctoral fellowship by the Center of Automotive Research at Stanfo
 rd (CARS). Before joining Stanford\, he finished his PhD at Vanderbilt Uni
 versity’s Computational Economics Research Lab and his doctoral thesis w
 as nominated for the Victor Lesser Distinguished Dissertation Award 2020. 
 His work on urban emergency response management has been covered in the Go
 vernment Technology Magazine and multiple global smart city summits\, and 
 received a best paper award at ICLR’s AI for Social Good Workshop.
LOCATION:https://ukri.zoom.us/j/92946956029
END:VEVENT
END:VCALENDAR