29
0

Kernel Multigrid: Accelerate Back-fitting via Sparse Gaussian Process Regression

Abstract

Additive Gaussian Processes (GPs) are popular approaches for nonparametric feature selection. The common training method for these models is Bayesian Back-fitting. However, the convergence rate of Back-fitting in training additive GPs is still an open problem. By utilizing a technique called Kernel Packets (KP), we prove that the convergence rate of Back-fitting is no faster than (1O(1n))t(1-\mathcal{O}(\frac{1}{n}))^t, where nn and tt denote the data size and the iteration number, respectively. Consequently, Back-fitting requires a minimum of O(nlogn)\mathcal{O}(n\log n) iterations to achieve convergence. Based on KPs, we further propose an algorithm called Kernel Multigrid (KMG). This algorithm enhances Back-fitting by incorporating a sparse Gaussian Process Regression (GPR) to process the residuals after each Back-fitting iteration. It is applicable to additive GPs with both structured and scattered data. Theoretically, we prove that KMG reduces the required iterations to O(logn)\mathcal{O}(\log n) while preserving the time and space complexities at O(nlogn)\mathcal{O}(n\log n) and O(n)\mathcal{O}(n) per iteration, respectively. Numerically, by employing a sparse GPR with merely 10 inducing points, KMG can produce accurate approximations of high-dimensional targets within 5 iterations.

View on arXiv
Comments on this paper