BEGIN:VCALENDAR
PRODID:-//eluceo/ical//2.0/EN
VERSION:2.0
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:www.tcs.tifr.res.in/event/1797
DTSTAMP:20261105T100303Z
SUMMARY:Great Expectations: Calibration and Its Consequences (Part 2)
DESCRIPTION:Speaker: Sagnik Chatterjee (TIFR)\n\nAbstract: \nA probabilisti
 c predictor $f:X\\to[0\,1]$ is calibrated if $\\mathbb{E}[Y\\mid f(X)]=f(X
 )$ almost surely. We start by briefly recalling the notion of approximate 
 calibration\, and finish the proof of the simple\, efficient deterministic
  predictor by Arunachaleswaran et al. (SODA 2025) that achieves $O(\\sqrt{
 T})$ distance to a perfectly calibrated prediction sequence over $T$ round
 s. If time permits\, we will revisit our discussion on the lack of stabili
 ty in approximate calibration measures like ECE and concretely define the 
 concepts of multicalibration and multiaccuracy. We will finish by discussi
 ng (without proof) a surprising result of Casacuberta et al. (FOCS 2025) w
 ho show that adding global calibration to multiaccuracy recovers much of t
 he learning-theoretic and complexity-theoretic power of multicalibration\,
  at a computational cost comparable to multiaccuracy alone.\n
URL:https://www.tcs.tifr.res.in/web/events/1797
DTSTART;TZID=Asia/Kolkata:20261106T160000
DTEND;TZID=Asia/Kolkata:20261106T170000
LOCATION:A-201 (STCS Seminar Room)
END:VEVENT
END:VCALENDAR