BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Statistical Risk Characterization of Penalized Likelihood Procedur
 es: An Information-Theoretic Determination - Andrew Barron\, Yale Universi
 ty
DTSTART:20131115T143000Z
DTEND:20131115T153000Z
UID:TALK47610@talks.cam.ac.uk
CONTACT:20082
DESCRIPTION:We review theory for the Minimum Description Length principle\
 , penalized likelihood and its statistical risk. An information theoretic 
 condition on a penalty pen(f) yields the conclusion that the optimizer of 
 the penalized log likelihood criterion log 1/likelihood(f) + pen(f) has ri
 sk not more than the index of resolvability\, corresponding to the accurac
 y of the optimizer of the expected value of the criterion.  For the linear
  span of a dictionary of candidate terms\, we develop the information theo
 retic validity of penalties based on the l_1 norm of the coefficients in r
 egression and log-density estimation settings. New results are presented f
 or Gaussian graphical models.  This represents joint work with Xi Luo and 
 Sabyasachi Chatterjee.
LOCATION:MR12\,  Centre for Mathematical Sciences\, Wilberforce Road\, Cam
 bridge
END:VEVENT
END:VCALENDAR