BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//hacksw/handcal//NONSGML v1.0//EN
BEGIN:VEVENT
UID:node-11349@prod.cs.cornell.edu
DTSTAMP:20200928T202000Z
DTSTART:20200928T202000Z
DTEND:20200928T212000Z
SUMMARY:Theory Seminar: An Equivalence Between Private Classification and Online Prediction
DESCRIPTION:Mark Bun, Boston University. An Equivalence Between Private Classification and Online Prediction (via Zoom)Abstract: Differential privacy enables rich statistical analyses on data while provably protecting individual-level privacy. The last 15 years of research has shown that, at least in principle, a number of fundamental statistical tasks are compatible with differential privacy. However, privacy-preserving analyses often require additional complexity over their non-private counterparts, for instance, in terms of the number of data samples one needs to collect in order to get accurate results. In fact, some infinite concept classes that are "easy" to learn in standard computational learning theory become impossible to learn under differential privacy using any finite number of samples....https://prod.cs.cornell.edu/content/theory-seminar-equivalence-between-private-classification-and-online-prediction
LOCATION:Streaming via Zoom
END:VEVENT
END:VCALENDAR