BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:A marginal sampler for σ-Stable Poisson-Kingman mixture models - 
 Maria Lomeli-Garcia (Gatsby Unit\, UCL)
DTSTART:20140924T100000Z
DTEND:20140924T110000Z
UID:TALK53694@talks.cam.ac.uk
CONTACT:Dr Jes Frellsen
DESCRIPTION:Infinite mixture models reposed on random probability measures
  like the Dirichlet process allow for flexible modelling of densities and 
 for clustering applications where the number of clusters is not fixed a pr
 iori. This is because we can formulate the problem as a hierarchical model
  where the top level is a (discrete) random probability measure. In recent
  years\, there has been a growing interest in using other random probabili
 ty measures\, beyond the classical Dirichlet process\, for extending model
 ling flexibility . Examples include Pitman-Yor processes\, normalized inve
 rse Gaussian processes\, and normalized random measures. Our understanding
  of these models has grown significantly over the last decade: there is an
  increasing realisation that while these models are nonparametric in natur
 e and allow an arbitrary number of components to be used\, they do impose 
 significant prior assumptions regarding the clustering structure. \n\nIn t
 his talk I will present a very wide class of random probability measures\,
  called σ-stable Poisson-Kingman processes\, and discuss its use for Baye
 sian nonparametric mixture modelling. This class of processes encompasses 
 most known random probability measures proposed in the literature so far\,
  and we argue that it forms a natural class to study. I will review certai
 n characterisations which lead us to propose a tractable and exact posteri
 or inference algorithm for the whole class. \n\n\nThis is joint work with 
 Yee Whye Teh and Stefano Favaro. The talk is based on our "preprint.":http
 ://arxiv.org/abs/1407.4211\n\n
LOCATION:Engineering Department\, CBL Room BE-438.
END:VEVENT
END:VCALENDAR