Lazy Gaussian Process Committee for Real-Time Online Regression

Authors

  • Han Xiao Technische Universität München
  • Claudia Eckert Technische Universität München

DOI:

https://doi.org/10.1609/aaai.v27i1.8572

Keywords:

Gaussian process, kernel method, regression, stream data, online learning, approximation, scalability

Abstract

A significant problem of Gaussian process (GP) is its unfavorable scaling with a large amount of data. To overcome this issue, we present a novel GP approximation scheme for online regression. Our model is based on a combination of multiple GPs with random hyperparameters. The model is trained by incrementally allocating new examples to a selected subset of GPs. The selection is carried out efficiently by optimizing a submodular function. Experiments on real-world data sets showed that our method outperforms existing online GP regression methods in both accuracy and efficiency. The applicability of the proposed method is demonstrated by the mouse-trajectory prediction in an Internet banking scenario.

Downloads

Published

2013-06-30

How to Cite

Xiao, H., & Eckert, C. (2013). Lazy Gaussian Process Committee for Real-Time Online Regression. Proceedings of the AAAI Conference on Artificial Intelligence, 27(1), 969-976. https://doi.org/10.1609/aaai.v27i1.8572