BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Algorithmic Approaches to Statistical Estimation under Structural 
 Constraints - Ilias Diakonikolas\, University of Edinburgh
DTSTART:20150206T160000Z
DTEND:20150206T170000Z
UID:TALK55591@talks.cam.ac.uk
CONTACT:20082
DESCRIPTION: The area of inference under structural (or shape) constraints
  --  that is\, inference about a probability distribution under the constr
 aint that its density function satisfies certain qualitative properties --
  is a classical topic in statistics and machine learning. Shape restricted
  inference has seen a recent surge of research activity\, in part due to t
 he ubiquity of structured distributions in the natural sciences. The hope 
 is that\, under such structural constraints\,  the quality of the resultin
 g estimators may dramatically improve\, both in terms of sample size and i
 n terms of computational efficiency.\n\nIn this talk\, we will describe a 
 framework that yields new\, provably efficient estimators for several natu
 ral and well-studied classes of distributions. Our approach relies on a si
 ngle\, unified algorithm that provides a fairly complete picture of the sa
 mple and computational complexities for fundamental inference tasks. The f
 ocus of the talk will be on density estimation (learning)\, but we may als
 o discuss applications of these ideas to hypothesis testing.
LOCATION:MR12\,  Centre for Mathematical Sciences\, Wilberforce Road\, Cam
 bridge
END:VEVENT
END:VCALENDAR