Picture of scraped petri dish

Scrape below the surface of Strathprints...

Explore world class Open Access research by researchers at the University of Strathclyde, a leading technological university.

Explore

Efficient Gaussian process based on BFGS updating and logdet approximation

Leithead, W.E. and Zhang, Y. and Leith, D.J. (2005) Efficient Gaussian process based on BFGS updating and logdet approximation. In: Proceedings of the 16th IFAC World Congress, 2005. UNSPECIFIED, p. 217. ISBN 978-3-902661-75-3

Full text not available in this repository. (Request a copy from the Strathclyde author)

Abstract

Gaussian process (GP) is a Bayesian nonparametric regression model, showing good performance in various applications. However, its hyperparameterestimation procedure suffers from numerous covariance-matrix inversions of prohibitively O(N3) operations. In this paper, we propose using the quasi-Newton BFGS O(N2)-operation formula to update recursively the inverse of covariance matrix at every iteration. As for the involved log det computation, a power-series expansion based approximation and compensation scheme is proposed with only 50N2 operations. A number of numerical tests are performed based on the 2D- sinusoidal regression example and the Wiener-Hammerstein identification example. It is shown that by using the proposed implementation, more than 80% O(N3) operations are eliminated, and the speedup of 5 - 9 can be achieved.