Publication :


Approximate Inference in Related Multi-output Gaussian Process Regression

Authors: A. Chiplunkar, E. Rachelson, M. Colombo and J. Morlier
Year: février 2017
Journal: Lecture Notes in Computer Science.
Volume: 10163, Pages: 88-103

DOI: 10.1007/978-3-319-53375-9_5

In Gaussian Processes a multi-output kernel is a covariance function over correlated outputs. Using a prior known relation between outputs, joint auto- and cross-covariance functions can be constructed. Realizations from these joint-covariance functions give outputs that are consistent with the prior relation. One issue with gaussian process regression is efficient inference when scaling upto large datasets. In this paper we use approximate inference techniques upon multi-output kernels enforcing relationships between outputs. Results of the proposed methodology for theoretical data and real world applications are presented. The main contribution of this paper is the application and validation of our methodology on a dataset of real aircraft flight tests, while imposing knowledge of aircraft physics into the model.

Bibtex citation :
Author={Chiplunkar, A. and Rachelson, E. and Colombo, M. and Morlier, J.},
Title={Approximate Inference in Related Multi-output Gaussian Process Regression},
Journal={Lecture Notes in Computer Science},
Volume={ 10163},

INSTITUT CLEMENT ADER, 3, rue Caroline Aigle F-31400 Toulouse, France.
Livraisons : +33 (0)5 61 17 10 07
Secrétariat ICA: +33 (0)5 61 17 10 85 ou +33 (0)5 61 17 10 82
Fax : +33 (0)5 61 17 10 80