BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Computational foundations of Bayesian inference and probabilistic 
 programming - Daniel Roy\, University of Cambridge
DTSTART:20140227T110000Z
DTEND:20140227T120000Z
UID:TALK51161@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:The complexity\, scale\, and variety of data sets we now have 
 access to have grown enormously\, and present exciting opportunities for n
 ew applications.  Just as high-level programming languages and compilers e
 mpowered experts to solve computational problems more quickly\, and made i
 t possible for non-experts to solve them at all\, a number of high-level p
 robabilistic programming languages with computationally universal inferenc
 e engines have been developed with the potential to similarly transform th
 e practice of Bayesian statistics.  These systems provide formal languages
  for specifying probabilistic models compositionally\, and general algorit
 hms for turning these specifications into efficient algorithms for inferen
 ce.\n\nIn this talk\, I will address three key questions at the theoretica
 l and algorithmic foundations of probabilistic programming---and probabili
 stic modelling more generally---that can be answered using tools from prob
 ability theory\, computability and complexity theory\, and nonparametric B
 ayesian statistics.  Which Bayesian inference problems can be automated\, 
 and which cannot?  Can probabilistic programming languages represent the s
 tochastic processes at the core of state-of-the-art nonparametric Bayesian
  models?  And if not\, can we construct useful approximations?  I’ll clo
 se by relating these questions to other challenges and opportunities ahead
  at the intersections of computer science\, statistics\, and probability.\
 n
LOCATION:Auditorium\, Microsoft Research Ltd\, 21 Station Road\, Cambridge
 \, CB1 2FB
END:VEVENT
END:VCALENDAR