BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CAIL//Events//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:CAIL Events
BEGIN:VEVENT
UID:2026-05-15-francis-bach@cail.columbia.edu
DTSTAMP:20260823T060817Z
DTSTART:20260515T150000Z
DTEND:20260515T160000Z
SUMMARY:ML Seminar: Francis Bach - Recent Advances in Uncertainty Quantifi
 cation: Anytime Guarantees and Multivariate Predictions
LOCATION:School of Social Work\, Room C03
DESCRIPTION:Quantifying uncertainty in statistics and machine learning is 
 crucial\, but challenging in high-dimensional prediction problems. Probabi
 listic calibration and conformal prediction have emerged as key practical 
 theoretically well-motivated frameworks. In this talk\, I will present rec
 ent advances that allow greater flexibility in their applications\, in ter
 ms of anytime guarantees and applications in multivariate prediction probl
 ems beyond univariate regression and binary classification.\n\nhttps://cai
 l.columbia.edu/events/2026-05-15-francis-bach
URL:https://cail.columbia.edu/events/2026-05-15-francis-bach
END:VEVENT
END:VCALENDAR