BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VTIMEZONE
TZID:Europe/Vienna
BEGIN:DAYLIGHT
DTSTART:20240331T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20231029T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260426T103450Z
UID:1701088500@ist.ac.at
DTSTART:20231127T133500
DTEND:20231127T143500
DESCRIPTION:Speaker: Rachel Cummings\nhosted by Monika Henzinger\nAbstract:
  Differential privacy (DP) is widely regarded as a gold standard for priva
 cy-preserving computation over users’ data.  It is a parameterized noti
 on of database privacy that gives a rigorous worst-case bound on the infor
 mation that can be learned about any one individual from the result of a d
 ata analysis task. Algorithmically it is achieved by injecting carefully c
 alibrated randomness into the analysis to balance privacy protections with
  accuracy of the results.In this talk\, we will survey recent developments
  in the development of DP algorithms for three important statistical probl
 ems\, namely online learning with bandit feedback\, causal inference\, and
  learning from imbalanced data. For the first problem\, we will show that 
 Thompson sampling -- a standard bandit algorithm developed in the 1930s --
  already satisfies DP due to the inherent randomness of the algorithm. For
  the second problem of causal inference and counterfactual estimation\, we
  develop the first DP algorithms for synthetic control\, which has been us
 ed non-privately for this task for decades. Finally\, for the problem of i
 mbalanced learning\, where one class is severely underrepresented in the t
 raining data\, we show that combining existing techniques such as minority
  oversampling perform very poorly when applied as pre-processing before a 
 DP learning algorithm\; instead we propose novel approaches for privately 
 generating synthetic minority points.Based on joint works with Marco Avell
 a Medina\, Vishal Misra\, Yuliia Lut\, Tingting Ou\, Saeyoung Rho\, Lucas 
 Rosenblatt\, Ethan Turok
LOCATION:Mondi 3\, ISTA
ORGANIZER:
SUMMARY:Rachel Cummings: Differentially Private Algorithms for Statistical 
 Estimation Problems
URL:https://talks-calendar.ista.ac.at/events/4617
END:VEVENT
END:VCALENDAR