Publikationsansicht

Fast Gaussian Process Regression using KD-Trees (2005)

Shen, Y.,
Ng, A.Y.,
Seeger, M.

Abstract

The computation required for Gaussian process regression with $n$ training examples is about $O(n^3)$ during training and $O(n)$ for each prediction. This makes Gaussian process regression too slow for large data sets. In this paper, we present a fast approximation method, based on kd-trees, that significantly reduces both the prediction and the training times of Gaussian process regression.

Details der Publikation

Download	http://edoc.mpg.de/270100
Archiv	Max Planck Society - eDocument Server (Germany)
Typ	Conference-Paper