BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20261006T210917EDT-3702whVV2m@132.216.98.100
DTSTAMP:20261007T010917Z
DESCRIPTION:\n	Abstract:\n\n\nWe consider point estimation and generation of
  confidence intervals under the constraint of differential privacy. We pro
 vide a simple and practical framework for these tasks in relatively genera
 l settings. Our investigation addresses a novel challenge that arises in t
 he differentially private setting\, which involves the cost of weak a prio
 ri bounds on the parameters of interest. This framework is applied to the 
 problems of Gaussian mean and covariance estimation. Despite the simplicit
 y of our method\, we are able to achieve minimax near-optimal rates for th
 ese problems. Empirical evaluations\, on the problems of mean estimation\,
  covariance estimation\, and principal component analysis\, demonstrate si
 gnificant improvements in comparison to previous work.\n\nNo knowledge of 
 differential privacy will be assumed. Based on joint works with Sourav Bis
 was\, Yihe Dong\, Jerry Li\, Vikrant Singhal\, and Jonathan Ullman.\n\n\n	S
 peaker\n\n\nDr. Gautam Kamath is an Assistant Professor at the University 
 of Waterloo’s Cheriton School of Computer Science\, and a faculty affiliat
 e at the Vector Institute. He is mostly interested in principled methods f
 or statistics and machine learning\, with a focus on settings which are co
 mmon in modern data analysis (high-dimensions\, robustness\, and privacy).
  He was a Microsoft Research Fellow at the Simons Institute for the Theory
  of Computing for the Fall 2018 semester program on Foundations of Data Sc
 ience and the Spring 2019 semester program on Data Privacy: Foundations an
 d Applications. Before that\, he completed his Ph.D. at MIT\, affiliated w
 ith the Theory of Computing group in CSAIL.\n\nZoom Link\n\nMeeting ID: 84
 3 0865 5572\n\nPasscode: 690084\n
DTSTART:20210226T203000Z
DTEND:20210226T213000Z
SUMMARY:Gautam Kamath (University of Waterloo)
URL:https://www.mcgill.ca/mathstat/channels/event/gautam-kamath-university-
 waterloo-329132
END:VEVENT
END:VCALENDAR