BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Combinatorial Stochastic Processes in Bayesian Nonparametrics - Cr
 eighton Heaukulani
DTSTART:20150319T150000Z
DTEND:20150319T163000Z
UID:TALK58580@talks.cam.ac.uk
CONTACT:Rowan McAllister
DESCRIPTION:*Abstract:*\n\nThe tutorial will cover the following topics:  
 Random partitions.  Random tree structures.  Random fragmentation and coag
 ulation processes.  These models have found usage in clustering and densit
 y modeling applications.  I will show you that each one of these structure
 s may be constructed from the previous.  Along the way\, we will also cove
 r how to study these objects from the perspective of random measures\, and
  we'll see why that perspective is so helpful\, not least because it helps
  us to better understand exchangeability.\n\nThe next topic is random feat
 ure allocations.  We will develop this theory\, which will seem to merely 
 mimic the theory of random partitions.  However\, I will in fact show you 
 how to construct random feature allocations from random partitions.  This 
 opens the door to constructing random feature allocations from random tree
  structures\, random fragmentations/coagulations\, and so on.  The potenti
 al applications for these models will be clear.\n\nThe theme of the talk i
 s using simple models to construct more elaborate ones.  The final bits of
  the talk are based on current work with Zoubin Ghahramani and Daniel M. R
 oy.\n\n\n*For preliminary reading:*\n# Ch. 2 of "The Nested Chinese Restau
 rant Process and Bayesian Nonparametric Inference of Topic Hierarchies":ht
 tps://cocosci.berkeley.edu/tom/papers/ncrp.pdf by Blei\, Griffiths\, and J
 ordan reviews the Chinese restaurant process\, so it will be very helpful 
 if you have little background on these things.  Ch. 3 covers nested Chines
 e restaurant processes in more detail than we will\, so not necessary but 
 may be good if you're keen.\n# For a background on the random measure pers
 pective\, I think Ch. 2 of "Sharing Clusters Among Related Groups: Hierarc
 hical Dirichlet Processes":http://www.stats.ox.ac.uk/~teh/research/npbayes
 /nips2004a.pdf by Teh\, Jordan\, Beal\, & Blei serves our purposes well.\n
 # For the feature allocations the obvious reference is "The Indian buffet 
 process: An introduction and review":http://www.jmlr.org/papers/v12/griffi
 ths11a.html by Griffiths and Ghahramani.  I would say Chs. 2 & 3 are excel
 lent motivation for appreciating the similar yet distinct approaches of pa
 rtitions vs. feature allocations.\n# For the random measure perspective in
  this case\, read the first 3 or 4 chapters of "Hierarchical beta processe
 s and the Indian buffet process":http://jmlr.org/proceedings/papers/v2/thi
 baux07a/thibaux07a.pdf by Thibaux & Jordan.
LOCATION:Engineering Department\, CBL Room 438
END:VEVENT
END:VCALENDAR