BEGIN:VCALENDAR
PRODID:-//eluceo/ical//2.0/EN
VERSION:2.0
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:www.tcs.tifr.res.in/event/1529
DTSTAMP:20250220T083032Z
SUMMARY:Robustness implies Privacy for Gaussian Mean Estimation
DESCRIPTION:Speaker: Malhar Ajit  Managoli (TIFR)\n\nAbstract: \nIn the tas
 k of parameter estimation\, robustness against corrupted samples and diffe
 rential privacy are two highly desirable properties.\nThese are also simil
 ar to each other in the sense that both require the estimator to not depen
 d too heavily on any one sample.\nIn this talk we will see how to design a
 n algorithm which is both robust and differentially private. In particular
 \, we will see a method\, known as the exponential mechanism\, which can b
 e used to turn certain types of robust algorithms into differentially priv
 ate ones.\n
URL:https://www.tcs.tifr.res.in/web/events/1529
DTSTART;TZID=Asia/Kolkata:20250221T160000
DTEND;TZID=Asia/Kolkata:20250221T170000
LOCATION:A-201 (STCS Seminar Room)
END:VEVENT
END:VCALENDAR