BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY: Variations of the Expectation due to Changes in the Measure: Appl
 ications to Generalization and Game Theory - Dr Samir Perlaza\, INRIA
DTSTART:20250226T140000Z
DTEND:20250226T150000Z
UID:TALK225298@talks.cam.ac.uk
CONTACT:Dr Amir R. Asadi
DESCRIPTION:In this talk\, closed-form expressions are presented for the v
 ariation of the expectation of a given function due to changes in the prob
 ability measure used for the expectation.  Two immediate applications are 
 found in statistical machine learning and game theory. The former leads to
  closed-form expressions for the generalization error of machine learning 
 algorithms. The latter leads to exact characterizations of the gain/loss o
 f players involved in a zero-sum game in which a player allows its opponen
 t to observe its action up to certain distortion.  In both cases\, these c
 haracterizations reveal interesting connections with Gibbs probability mea
 sures\, mutual information\, and lautum information.
LOCATION:MR5\, CMS Pavilion A
END:VEVENT
END:VCALENDAR