BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Using Context and Insight for the Analysis of LittleData? - Philip
 p Moritz (U Cambridge)
DTSTART:20130308T110000Z
DTEND:20130308T113000Z
UID:TALK43896@talks.cam.ac.uk
CONTACT:Zoubin Ghahramani
DESCRIPTION:We live in the era of Big Data with many interesting challenge
 s for Machine Learning. In the opposite regime of "Little Data"\, a limite
 d population size\, limited measurement time or a limited budget constrain
 s the amount of data available. Examples include magnetic resonance imagin
 g\, microarray experiments or portfolio management. To obtain sensible pre
 dictions it is then crucial to take modeling assumptions into account. In 
 this talk I will cover challenges\, both computational and conceptual\, th
 at come up in the presence of a limited amount of data and how they can be
  overcome. I will focus on causality and high-dimensional covariance estim
 ation and present a new algorithm that allows to compute an asymptotically
  unbiased\, sparse and positive semidefinite estimator for covariance matr
 ices using the SCAD penalty from high-dimensional statistics.
LOCATION:Engineering Department\, CBL Room BE-438
END:VEVENT
END:VCALENDAR