BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Learning of Milky Way Model Parameters Using Matrix-variate Data i
 n a New Gaussian Process-based Method - Dr Dalia Chakrabarty (University o
 f Warwick)
DTSTART:20121115T113000Z
DTEND:20121115T123000Z
UID:TALK41422@talks.cam.ac.uk
CONTACT:Zoubin Ghahramani
DESCRIPTION:In this talk I will discuss a new Bayesian non-parametric meth
 od of predicting the value of the model parameter vector that supports rea
 l observed data\, where this measured information is in the form of a matr
 ix. The information is then expressed as an unknown\, matrix-variate funct
 ion of the model parameter vector and this unknown function is modelled us
 ing a high-dimensional Gaussian Process. The model is trained on a trainin
 g data set that is generated (via simulations) at a chosen design set. In 
 fact\, in our treatment of the information as a vector of corresponding di
 mensions\, this function is modelled as a vector-variate Gaussian Process 
 leading to the likelihood being matrix-normal in nature\, with mean and co
 variance matrices suggested by the structure of the Gaussian Process in qu
 estion. In an effort to learn selected process parameters (such as the smo
 othness parameters) from the data\, in addition to the unknown model param
 eter vector value that supports the real data\, we write their joint poste
 rior probability\, given training as well as observed data. Inference is p
 erformed using Transformation-based MCMC. An application of this method is
  made to learn feature parameters of the Milky Way\, using measured and si
 mulated data of velocity vectors of stars that live in the vicinity of the
  Sun. Learning of the Galactic parameters with the real data is shown to p
 roduce a similar result to a comparator method that requires a much larger
  data set\, in order to accomplish estimation.\n
LOCATION:Engineering Department\, CBL Room BE-438
END:VEVENT
END:VCALENDAR