BEGIN:VCALENDAR
PRODID:-//eluceo/ical//2.0/EN
VERSION:2.0
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:www.tcs.tifr.res.in/event/1697
DTSTAMP:20260227T042429Z
SUMMARY:Nash Regret and Beyond: Optimal Fairness Guarantees in Bandit Probl
 ems
DESCRIPTION:Speaker: Sayak Ray Chowdhury (IIT Kanpur)\n\nAbstract: \nTradit
 ional regret minimization in multi-armed bandits focuses on maximizing cum
 ulative reward\, often overlooking fairness across individuals receiving o
 utcomes. Motivated by applications such as clinical trials and resource al
 location\, Nash regret has been proposed as a fairness-aware metric based 
 on the geometric mean of rewards. In this talk\, I will present recent res
 ults showing that near-optimal Nash regret can be achieved using simple an
 d general bandit algorithms under mild assumptions in stochastic bandits\,
  along with extensions to a broader class of power-mean fairness objective
 s. I will then discuss fairness in linear bandits\, where we obtain the fi
 rst order-optimal Nash regret bounds in dimension and introduce a generic 
 meta-algorithm that converts standard linear bandit methods into fairness-
 aware versions with provable guarantees. Empirical results demonstrate con
 sistent improvements over existing approaches. Overall\, the work highligh
 ts that fairness can be incorporated into bandit learning without sacrific
 ing statistical efficiency.\nShort Bio: Sayak Ray Chowdhury is an Assista
 nt Professor in the Department of Computer Science and Engineering at the 
 Indian Institute of Technology Kanpur. His research focuses on sequential 
 decision making under uncertainty\, including multi-armed bandits\, reinfo
 rcement learning\, and language model alignment\, as well as on privacy an
 d fairness in ML. Prior to joining IIT Kanpur\, he was a Postdoctoral Rese
 archer at Microsoft Research India and Boston University. He received his 
 Ph.D. from the Indian Institute of Science (IISc) Bangalore. He is a recip
 ient of the INAE Young Associate award from the Indian National Academy of
  Engineering.\n
URL:https://www.tcs.tifr.res.in/web/events/1697
DTSTART;TZID=Asia/Kolkata:20260304T160000
DTEND;TZID=Asia/Kolkata:20260304T170000
LOCATION:A-201 (STCS Seminar Room)
END:VEVENT
END:VCALENDAR