Call for Abstracts and Participation
NIPS 2009 WORKSHOP on NONPARAMETRIC BAYES
December 11/12, 2009
abstract submission deadline: Wednesday, October 21st
One of the major problems driving current research in statistical machine learning is the search for ways to exploit highly-structured models that are both expressive and tractable. Bayesian nonparametrics provides a framework for developing robust and flexible models that can accurately represent the complex structure in the data. Model flexibility is achieved by assigning priors with unbounded capacity and overfitting is prevented by integrating out all parameters and
Current work has established results on asymptotic behaviour of simple Bayesian nonparametric models. Most of the results are for simple cases, such as density estimation and Gaussian process regression. However, there is a steady development of tools, which are starting to allow us to tackle much more challenging models. We have invited experts to comment and provide guidance on discussion on this topic. We also invite theoreticians within the NIPS community to participate
in this focus.
It is essential to provide easy to follow guidance for the model structure specification and the choice of hyperparameters. A step towards this direction is the discussion of an objective or empirical Bayes treatment. Additionally, developing general purpose software that can scale up inference techniques to massive datasets would is another step necessary for the wide applicability of these models. This workshop will help us summarize the current state of the
practical use of nonparametric Bayesian models and focus on the requirements of the field to extend its use in other application domains.
We aim to bring together researchers to create a forum for discussing recent advances in Bayesian nonparametrics, to understand better the asymptotic properties of the models and to inspire research on new techniques for better models and inference algorithms. The workshop will focus mainly on two important issues. 1) Theoretical properties of complex Bayesian nonparametric models, in particular asymptotics (e.g. consistency, rates of convergence, and Bernstein von- Mises results). 2) Practical matters to enable the use of Bayesian nonparametrics in real world applications such as developing general purpose software, discussion of an objective or empirical Bayes treatment. Each focus will be given a specific session during the workshop.
This is the fifth in a series of successful workshops on this topic. The first two were at NIPS 2003 and 2005 and the last two were at ICML 2006 and 2008. The field attracts researchers from a broad range of disciplines, ranging from theoretical statisticians and probabilists to people working on specialized applications. This workshop aims to enhance the interaction between these communities which has been initiated by previous workshops in order to exchange ideas, discuss
future directions, and build collaborative efforts.
The workshop will consist of 5 invited talks, 4 contributed talks, a session for informal impromptu talks and a poster session.
INVITED SPEAKERS (confirmed)
Zoubin Ghahramani, University of Cambridge
Subhashis Ghoshal, North Carolina State University
Tom Griffiths, University of California, Berkeley
Alejandro Jara, Universidad de Concepción
CALL FOR PARTICIPATION
Researchers interested in presenting their work and ideas on Bayesian nonparametrics at the workshop should send an email to npbayes2009 (at) googlemail.com with the following information:
Abstract (maximum 3 pages, NIPS style pdf)
Preferred contribution (talk, poster, and/or round-table
We expect authors to provide a final version of their papers by early December for inclusion on the workshop home page. Papers chosen for contributed talks shall also be expected to liaise with a discussion leader who will be in charge of stimulating discussion of the work at the workshop.
Abstracts due: Oct 21, 2009
Notifications: Nov 4, 2009
Final paper due: Dec 2, 2009
Workshop: Dec 11/12, 2009
Westin Resort and Spa / Hilton Whistler Resort and Spa
Whistler, B.C., Canada
Dilan Gorur, Gatsby Computational Neuroscience Unit
François Caron, INRIA Bordeaux Sud-Ouest
Yee Whye Teh, Gatsby Computational Neuroscience Unit
David Dunson, Duke University
Zoubin Ghahramani, University of Cambridge
Michael I. Jordan, University of California at Berkeley
Your expertise, experience and perspective are very valuable to making the workshop a success. Thank you very much, and we hope to see you at the workshop!
Dilan Gorur, François Caron, Yee Whye Teh, David Dunson, Zoubin
Ghahramani and Michael I. Jordan.