BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//EE - ECPv5.10.0//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:EE
X-ORIGINAL-URL:https://ee.iisc.ac.in
X-WR-CALDESC:Events for EE
BEGIN:VTIMEZONE
TZID:Asia/Kolkata
BEGIN:STANDARD
TZOFFSETFROM:+0530
TZOFFSETTO:+0530
TZNAME:IST
DTSTART:20230101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Asia/Kolkata:20231221T110000
DTEND;TZID=Asia/Kolkata:20231221T130000
DTSTAMP:20260416T192545
CREATED:20231218T044331Z
LAST-MODIFIED:20231218T044331Z
UID:241280-1703156400-1703163600@ee.iisc.ac.in
SUMMARY:[EE/CPS Seminar] Apurv Shukla - Differentially Private Online Resource Allocation
DESCRIPTION:EE/CPS SeminarSpeaker: Apurv ShuklaPostdoctoral Associate at Texas A&M UniversityTitle: Differentially Private Online Resource AllocationDate: Thursday\, 21 December 2023Time: 11amVenue: EE MMCR (C241)Abstract:We consider an online resource allocation problem when thedecision-maker wishes to preserve the privacy of incoming arrivals andrewards. We present a family of algorithms based on private meanestimation and primal-dual schemes that achieve optimal utilityguarantees. We establish utility and privacy bounds on the behavior ofalgorithms in this family under minimal assumptions on the arrivalprocess. These results are further corroborated by a set of numericalexperiments that demonstrate the tightness of our bounds.Biography of the speaker:Apurv is a Postdoctoral Associate at Texas A&M working with Prof. Le Xieand Prof. PR Kumar. His research interest lies in learning and controlwith applications in power systems. He obtained his PhD from ColumbiaUniversity and his bachelor’s degree from IIT Kharagpur.
URL:https://ee.iisc.ac.in/event/ee-cps-seminar-apurv-shukla-differentially-private-online-resource-allocation/
LOCATION:MMCR\, Hall C 241\, 1st floor\, EE department
END:VEVENT
END:VCALENDAR