Fast Allocation of Gaussian Process Experts

Trung Nguyen, Edwin Bonilla
; Proceedings of the 31st International Conference on Machine Learning, PMLR 32(1):145-153, 2014.

Abstract

We propose a scalable nonparametric Bayesian regression model based on a mixture of Gaussian process (GP) experts and the inducing points formalism underpinning sparse GP approximations. Each expert is augmented with a set of inducing points, and the allocation of data points to experts is defined probabilistically based on their proximity to the experts. This allocation mechanism enables a fast variational inference procedure for learning of the inducing inputs and hyperparameters of the experts. When using K experts, our method can run K^2 times faster and use K^2 times less memory than popular sparse methods such as the FITC approximation. Furthermore, it is easy to parallelize and handles non-stationarity straightforwardly. Our experiments show that on medium-sized datasets (of around 10^4 training points) it trains up to 5 times faster than FITC while achieving comparable accuracy. On a large dataset of 10^5 training points, our method significantly outperforms six competitive baselines while requiring only a few hours of training.

Cite this Paper


BibTeX
@InProceedings{pmlr-v32-nguyena14, title = {Fast Allocation of Gaussian Process Experts}, author = {Trung Nguyen and Edwin Bonilla}, booktitle = {Proceedings of the 31st International Conference on Machine Learning}, pages = {145--153}, year = {2014}, editor = {Eric P. Xing and Tony Jebara}, volume = {32}, number = {1}, series = {Proceedings of Machine Learning Research}, address = {Bejing, China}, month = {22--24 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v32/nguyena14.pdf}, url = {http://proceedings.mlr.press/v32/nguyena14.html}, abstract = {We propose a scalable nonparametric Bayesian regression model based on a mixture of Gaussian process (GP) experts and the inducing points formalism underpinning sparse GP approximations. Each expert is augmented with a set of inducing points, and the allocation of data points to experts is defined probabilistically based on their proximity to the experts. This allocation mechanism enables a fast variational inference procedure for learning of the inducing inputs and hyperparameters of the experts. When using K experts, our method can run K^2 times faster and use K^2 times less memory than popular sparse methods such as the FITC approximation. Furthermore, it is easy to parallelize and handles non-stationarity straightforwardly. Our experiments show that on medium-sized datasets (of around 10^4 training points) it trains up to 5 times faster than FITC while achieving comparable accuracy. On a large dataset of 10^5 training points, our method significantly outperforms six competitive baselines while requiring only a few hours of training.} }
Endnote
%0 Conference Paper %T Fast Allocation of Gaussian Process Experts %A Trung Nguyen %A Edwin Bonilla %B Proceedings of the 31st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2014 %E Eric P. Xing %E Tony Jebara %F pmlr-v32-nguyena14 %I PMLR %J Proceedings of Machine Learning Research %P 145--153 %U http://proceedings.mlr.press %V 32 %N 1 %W PMLR %X We propose a scalable nonparametric Bayesian regression model based on a mixture of Gaussian process (GP) experts and the inducing points formalism underpinning sparse GP approximations. Each expert is augmented with a set of inducing points, and the allocation of data points to experts is defined probabilistically based on their proximity to the experts. This allocation mechanism enables a fast variational inference procedure for learning of the inducing inputs and hyperparameters of the experts. When using K experts, our method can run K^2 times faster and use K^2 times less memory than popular sparse methods such as the FITC approximation. Furthermore, it is easy to parallelize and handles non-stationarity straightforwardly. Our experiments show that on medium-sized datasets (of around 10^4 training points) it trains up to 5 times faster than FITC while achieving comparable accuracy. On a large dataset of 10^5 training points, our method significantly outperforms six competitive baselines while requiring only a few hours of training.
RIS
TY - CPAPER TI - Fast Allocation of Gaussian Process Experts AU - Trung Nguyen AU - Edwin Bonilla BT - Proceedings of the 31st International Conference on Machine Learning PY - 2014/01/27 DA - 2014/01/27 ED - Eric P. Xing ED - Tony Jebara ID - pmlr-v32-nguyena14 PB - PMLR SP - 145 DP - PMLR EP - 153 L1 - http://proceedings.mlr.press/v32/nguyena14.pdf UR - http://proceedings.mlr.press/v32/nguyena14.html AB - We propose a scalable nonparametric Bayesian regression model based on a mixture of Gaussian process (GP) experts and the inducing points formalism underpinning sparse GP approximations. Each expert is augmented with a set of inducing points, and the allocation of data points to experts is defined probabilistically based on their proximity to the experts. This allocation mechanism enables a fast variational inference procedure for learning of the inducing inputs and hyperparameters of the experts. When using K experts, our method can run K^2 times faster and use K^2 times less memory than popular sparse methods such as the FITC approximation. Furthermore, it is easy to parallelize and handles non-stationarity straightforwardly. Our experiments show that on medium-sized datasets (of around 10^4 training points) it trains up to 5 times faster than FITC while achieving comparable accuracy. On a large dataset of 10^5 training points, our method significantly outperforms six competitive baselines while requiring only a few hours of training. ER -
APA
Nguyen, T. & Bonilla, E.. (2014). Fast Allocation of Gaussian Process Experts. Proceedings of the 31st International Conference on Machine Learning, in PMLR 32(1):145-153

Related Material