Connectionists: Call for abstracts: NIPS 06 workshop on Dynamical Systems, Stochastic Processes and Bayesian Inference

[Cedric Archambeau]

Apologies for cross-posting.


CALL FOR ABSTRACTS:

====================================================
NIPS 2006 Workshop on
Dynamical Systems, Stochastic Processes and Bayesian Inference
====================================================

http://www.cs.ucl.ac.uk/staff/c.archambeau/dsb.htm

December 8-9, Whistler, BC, Canada

[Abstract submission deadline: November 1, 2006]


OVERVIEW:

The modelling of continuous-time dynamical systems from uncertain 
observations is an important task that comes up in a wide range of 
applications ranging from numerical weather prediction over finance to 
genetic networks and motion capture in video. Often, we may assume that 
the dynamical models are formulated by systems of differential 
equations. In a Bayesian approach, we may then incorporate a priori 
knowledge about the dynamics by providing probability distributions on 
the unknown functions, which correspond for example to driving forces 
and appear as coefficients or parameters in the differential equations. 
Hence, such functions become stochastic processes in a probabilistic 
Bayesian framework.

Gaussian processes (GPs) provide a natural and flexible framework in 
such circumstances. The use of GPs in the learning of functions from 
data is now a well-established technique in Machine Learning. 
Nevertheless, their application to dynamical systems becomes highly 
nontrivial when the dynamics is nonlinear in the (Gaussian) parameter 
functions. This happens naturally for nonlinear systems which are driven 
by a Gaussian noise process, or when the nonlinearity is needed to 
provide necessary constraints (e.g., positivity) for the parameter 
functions. In such a case, the prior process over the system's dynamics 
is non-Gaussian right from the start. This means, that closed form 
analytical posterior predictions (even in the case of Gaussian 
observation noise) are no longer possible. Moreover, their computation 
requires the entire underlying Gaussian latent process at all times (not 
just at the discrete observation times). Hence, inference of the 
dynamics would require nontrivial sampling methods or approximation 
techniques.

This raises the following questions:

- What is the practical relevance of nonlinear effects, i.e. could we 
just ignore them?
- How should we sample randomly from posterior continuous-time processes?
- How should we deal with large data sets and/or very high dimensional data?
- Are functional Laplace approximations suitable?
- Can we think of variational approximations?
- Can we do parameter and hyper-parameter estimation?
- Etc.

The aim of this workshop is to provide a forum for discussing open 
problems related to continuous-time stochastic dynamical systems, their 
links to Bayesian inference and their relevance to Machine Learning. The 
workshop will be of interest to workers in both Bayesian Inference and 
Stochastic Processes. We hope that the workshop will provide new 
insights in continous-time stochastic processes and serve as a starting 
point for new research perspectives and future collaborations.


SUBMISSIONS:

We welcome extended abstract submissions to the NIPS 2006 workshop on 
"Dynamical Systems, Stochastic Processes and Bayesian Inference" in the 
following related areas (but not restricted to):

- Nonlinear dynamical systems
- Bayesian inference in stochastic processes
- Gaussian and non-Gaussian processes
- Continuous-time Markov chains
- Continuous-time discrete/continuous state processes
- Gaussian, mixture of Gaussians and nonparametric belief networks
- Nonlinear filtering/smoothing

The suggested abstract length is 4 pages (maximum 8 pages), formatted in 
the NIPS format. The abstracts will be made available on the web. The 
authors should submit their extended abstract to dsb at cs.ucl.ac.uk in PDF 
before Nov. 1, 2006, 23:59 UTC. An email confirming the reception of the 
submission will be sent by the organizers.

Further requests, suggestions and comments should be sent to 
dsb at cs.ucl.ac.uk.


SCHEDULE:

Oct. 01: Call for extended abstracts
Nov. 01: Abstract submission deadline
Nov. 17: Notification of acceptance
Nov. 24: Final extended abstracts due
Dec. 8 or 9: Workshop


PROGRAM:

In order to encourage an active participation of the attendees, both, 
the morning and the afternoon session will include invited talks, short 
peer-reviewed spotlights presentations, and extended poster sessions for 
informal discussions. The workshop will close with a wrap-up.


SPEAKERS:

Neil Lawrence, University of Sheffield.
Manfred Opper, Technical University Berlin.
Chris Williams, University of Edingburgh.


ORGANIZERS:

Cedric Archambeau, University College, London.
Manfred Opper, Technical University, Berlin.
John Shawe-Taylor, University College, London.


PROGRAM COMMITTEE:

Cedric Archambeau, University College, London.
Dan Cornford, Aston University.
Manfred Opper, Technical University, Berlin.
John Shawe-Taylor, University College, London.
Magnus Rattray, University of Manchester.