BEGIN:VCALENDAR
PRODID:-//eluceo/ical//2.0/EN
VERSION:2.0
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:www.tcs.tifr.res.in/event/558
DTSTAMP:20230914T125929Z
SUMMARY:Efficient Detection and Localization on Graph Structured Data
DESCRIPTION:Speaker: Manjesh Kumar Hanawal (Boston University\nPostdoctoral
  Associate\nOne Siber Way\nBoston. MA 02215\nUnited States of America)\n\n
 Abstract: \nAbstract: We consider stochastic sequential learning problems 
 where the learner can observe the average reward of several actions. Such 
 a setting is interesting in many applications involving monitoring and su
 rveillance\, where the set of the actions to observe represent some (geogr
 aphical) area. The importance of this setting is that in these application
 s\, it is actually cheaper to observe average reward of a group of actions
  rather than the reward of a single action. We show that when the reward i
 s smooth over a given graph representing the neighboring actions\, we can 
 maximize the cumulative reward of learning while minimizing the sensing c
 ost. We propose CheapUCB\, an algorithm that matches the regret guarantees
  of the known algorithms for this setting and at the same time guarantees 
 a linear cost again over them.\n\nBio: Manjesh Kumar Hanawal received Ph.D
 . degree at INRIA\, Sophia Antipolis\, France\, and the University d’Avi
 gnon\, Avignon\, France in 2013. Before this he received B.E. degree in el
 ectronics and communication from the National Institute of Technology\, Bh
 opal\, India \, and the M.Sc. degree in electrical communication engineeri
 ng from the Indian Institute of Science\, Bangalore\, India. Currently\, h
 e is a Postdoctoral associate at Boston University\, USA. His bachelor's s
 tudies was sponsored by Airtel India selecting him as a Bharti scholar. Hi
 s masters’ thesis was awarded best M.Sc. thesis medal (Prof. F. M. Mowda
 walla Medal)\, and he is recipient of INSPIRE faculty fellowship from DST\
 , Government of India.\n\nFrom 2004 to 2007\, he was with the Centre for A
 rtificial Intelligence and Robotics (CAIR)\, DRDO\, Bangalore\, as Scienti
 st-B.\n
URL:https://www.tcs.tifr.res.in/web/events/558
DTSTART;TZID=Asia/Kolkata:20141219T143000
DTEND;TZID=Asia/Kolkata:20141219T153000
LOCATION:D-405 (D-Block Seminar Room)
END:VEVENT
END:VCALENDAR