Expectation Propagation in Gaussian Process Dynamical Systems

File Description SizeFormat 
nips2012.pdfAccepted version570.97 kBAdobe PDFDownload
Title: Expectation Propagation in Gaussian Process Dynamical Systems
Author(s): Deisenroth, MP
Mohamed, S
Item Type: Conference Paper
Abstract: Rich and complex time-series data, such as those generated from engineering systems, financial markets, videos, or neural recordings are now a common feature of modern data analysis. Explaining the phenomena underlying these diverse data sets requires flexible and accurate models. In this paper, we promote Gaussian process dynamical systems as a rich model class that is appropriate for such an analysis. We present a new approximate message-passing algorithm for Bayesian state estimation and inference in Gaussian process dynamical systems, a nonparametric probabilistic generalization of commonly used state-space models. We derive our message-passing algorithm using Expectation Propagation and provide a unifying perspective on message passing in general state-space models. We show that existing Gaussian filters and smoothers appear as special cases within our inference framework, and that these existing approaches can be improved upon using iterated message passing. Using both synthetic and real-world data, we demonstrate that iterated message passing can improve inference in a wide range of tasks in Bayesian state estimation, thus leading to improved predictions and more effective decision making.
Publication Date: 1-Dec-2012
URI: http://hdl.handle.net/10044/1/11568
ISBN: 9781627480031
Publisher: The MIT Press
Start Page: 1
End Page: 9
Journal / Book Title: Advances in Neural Information Processing Systems (NIPS 2012)
Copyright Statement: © 2012 The Authors
Conference Name: NIPS 2012
Publisher URL: http://www.proceedings.com/17576.html
Start Date: 2012-12-03
Finish Date: 2012-12-08
Conference Place: Lake Tahoe, Nevada
Appears in Collections:Computing

Items in Spiral are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commons