Gaussian Process Random Fields
Dave Moore · Stuart J Russell

Wed Dec 9th 07:00 -- 11:59 PM @ 210 C #29 #None

Gaussian processes have been successful in both supervised and unsupervised machine learning tasks, but their computational complexity has constrained practical applications. We introduce a new approximation for large-scale Gaussian processes, the Gaussian Process Random Field (GPRF), in which local GPs are coupled via pairwise potentials. The GPRF likelihood is a simple, tractable, and parallelizeable approximation to the full GP marginal likelihood, enabling latent variable modeling and hyperparameter selection on large datasets. We demonstrate its effectiveness on synthetic spatial data as well as a real-world application to seismic event location.

Author Information

Dave Moore (UC Berkeley)
Stuart J Russell (UC Berkeley)

More from the Same Authors