Fast Forward Selection to Speed Up Sparse Gaussian Process Regression

Fast Forward Selection to Speed Up Sparse Gaussian Process Regression (2003)

Cached

Download Links

by Matthias Seeger , Christopher K. I. Williams , Neil D. Lawrence , Sheeld S Dp

Venue:	in Workshop on AI and Statistics 9
Citations:	54 - 2 self

BibTeX

@INPROCEEDINGS{Seeger03fastforward,
    author = {Matthias Seeger and Christopher K. I. Williams and Neil D. Lawrence and Sheeld S Dp},
    title = {Fast Forward Selection to Speed Up Sparse Gaussian Process Regression},
    booktitle = {in Workshop on AI and Statistics 9},
    year = {2003}
}

Years of Citing Articles

Bookmark

OpenURL

Abstract

We present a method for the sparse greedy approximation of Bayesian Gaussian process regression, featuring a novel heuristic for very fast forward selection. Our method is essentially as fast as an equivalent one which selects the "support" patterns at random, yet it can outperform random selection on hard curve fitting tasks. More importantly, it leads to a suciently stable approximation of the log marginal likelihood of the training data, which can be optimised to adjust a large number of hyperparameters automatically.

Citations

6694	Statistical Learning Theory - Vapnik - 1998
380	Sparse Bayesian learning and the Relevance Vector Machine - Tipping
243	Smopolinsky H: Query by committee - Seung, Opper - 1992
207	Using the nyström method to speed up kernel machines - Williams, Seeger
119	Evaluation of Gaussian Processes and other Methods for Non-Linear Regression - Rasmussen - 1996
93	Sparse greedy gaussian process regression - Smola, Bartlett - 2001
88	Sparse on-line Gaussian processes - Csató, Opper
87	Fast sparse Gaussian Process method: Informative vector machines. NIPS - Lawrence, Seeger, et al. - 2002
79	Bayesian Gaussian Process for Regression and Classification - Gibbs - 1997
60	A Bayesian committee machines - Tresp - 2000
48	Hybrid adaptive splines - Luo, Wahba - 1997
16	Observations on the Nyström method for Gaussian process prediction - Williams, Rasmussen, et al. - 2002
9	Tap gibbs free energy, belief propagation and sparsity - Csato, Opper, et al. - 2001
1	Variational Gaussian process classi - Gibbs, MacKay - 1997