BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Informational Geometry - Nilesh Tripuraneni\, Shane Gu
DTSTART:20150402T140000Z
DTEND:20150402T153000Z
UID:TALK58582@talks.cam.ac.uk
CONTACT:Rowan McAllister
DESCRIPTION:*Abstract:* \nWe will review the max-ent interpretation of exp
 onential families\, and it's connection to information projections. After 
 exploring some simple results about I-projections\, Fisher information\, a
 nd their relation to ideas in machine learning\, we will explain how to ge
 ometrically interpret AdaBoost in this framework. \n\n*Optional Background
 :* \nFamiliarity with Lagrange Multipliers/Lagrange duality will be helpfu
 l
LOCATION:Engineering Department\, CBL Room 438
END:VEVENT
END:VCALENDAR