BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Ranking from pairwise comparisons using Seriation - Alexandre d'As
 premont\, CNRS &amp\; Ecole Normale Supérieure\, Paris
DTSTART:20141107T160000Z
DTEND:20141107T170000Z
UID:TALK54671@talks.cam.ac.uk
CONTACT:20082
DESCRIPTION:We describe a seriation algorithm for ranking a set of n items
  given pairwise comparisons between these items. Intuitively\, the algorit
 hm assigns similar rankings to items that compare similarly with all other
 s. It does so by constructing a similarity matrix from pairwise comparison
 s\, using seriation methods to reorder this matrix and construct a ranking
 . We first show that this spectral seriation algorithm recovers the true r
 anking when all pairwise comparisons are observed and consistent with a to
 tal order. We then show that ranking reconstruction is still exact even wh
 en some pairwise comparisons are corrupted or missing\, and that seriation
  based spectral ranking is more robust to noise than other scoring methods
 . An additional benefit of the seriation formulation is that it allows us 
 to solve semi-supervised ranking problems. Experiments on both synthetic a
 nd real datasets demonstrate that seriation based spectral ranking achieve
 s competitive and in some cases superior performance compared to classical
  ranking methods.\n\nJoint work with Fajwel Fogel (Ecole Polytechnique) an
 d Milan Vojnovic (MSR Cambridge)
LOCATION:MR12\,  Centre for Mathematical Sciences\, Wilberforce Road\, Cam
 bridge
END:VEVENT
END:VCALENDAR