BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Efficient and Parsimonious Agnostic Active Learning - Alekh Agarwa
 l (Microsoft Research NY) 
DTSTART:20151106T143000Z
DTEND:20151106T153000Z
UID:TALK61087@talks.cam.ac.uk
CONTACT:Quentin Berthet
DESCRIPTION:We develop a new active learning algorithm for the streaming s
 etting satisfying three important properties: 1) It provably works for any
  classifier representation and classification problem including those with
  severe noise. 2) It is efficiently implementable with an ERM oracle. 3) I
 t is more aggressive than all previous approaches satisfying 1 and 2. To d
 o this we create an algorithm based on a newly defined optimization proble
 m and analyze it. We also conduct the first experimental analysis of all e
 fficient agnostic active learning algorithms\, evaluating their strengths 
 and weaknesses in different settings.\n\nThis is joint work with Tzu-Kuo H
 uang\, John Langford and Rob Schapire at Microsoft Research.
LOCATION:MR12\, Centre for Mathematical Sciences\, Wilberforce Road\, Camb
 ridge.
END:VEVENT
END:VCALENDAR