BEGIN:VCALENDAR
PRODID:-//eluceo/ical//2.0/EN
VERSION:2.0
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:www.tcs.tifr.res.in/event/1653
DTSTAMP:20260105T044829Z
SUMMARY:Infinitely divisible privacy and beyond I: resolution of the s^2=2k
  conjecture
DESCRIPTION:Speaker: Aaradhya Pandey (Princeton University)\n\nAbstract: \n
 In this talk\, I will begin by introducing a hypothesis-testing-based form
 ulation of differential privacy in classical computation. The Gaussian Dif
 ferential Privacy paper (Dong–Roth–Su '22) established a central limit
  theorem for the composition of multiple private mechanisms. Building on t
 his\, I will present a Poisson extension of their result and show how both
  the Gaussian and Poisson limits are unified under the framework of infin
 itely divisible privacy\, revealing connections to statistics\, probabilit
 y\, and discrete mathematics. I will conclude with discussions on quantiz
 ing privacy in quantum computation and deriving central limit theorems in
  a framework of quantum differential privacy.\n \nShort Bio:  Aaradhya 
 is a fifth-year PhD Student at Princeton ORFE. He completed his Bachelor's
  in mathematics at IISc in 2021. His research interests are at the interfa
 ce of probability theory\, statistics\, and information theory with ap
 plications in (quantum) differential privacy\, machine unlearning\, and
  spin glasses. When most approaches in a field are analytic\, he tries to
  develop algebraic ones — and vice versa.\n
URL:https://www.tcs.tifr.res.in/web/events/1653
DTSTART;TZID=Asia/Kolkata:20260113T160000
DTEND;TZID=Asia/Kolkata:20260113T170000
LOCATION:via Zoom in A201
END:VEVENT
END:VCALENDAR