BriefGPT.xyz
Feb, 2018
可扩展高斯过程的产品核插值
Product Kernel Interpolation for Scalable Gaussian Processes
HTML
PDF
Jacob R. Gardner, Geoff Pleiss, Ruihan Wu, Kilian Q. Weinberger, Andrew Gordon Wilson
TL;DR
本文提出了一种基于矩阵向量乘法和乘积核结构的新技术，可以在高维空间中实现快速的Kernel学习，并实现了令人瞩目的多任务GPs性能。
Abstract
Recent work shows that inference for
gaussian processes
can be performed efficiently using iterative methods that rely only on matrix-vector multiplications (MVMs).
structured kernel interpolation
(SKI) exploits
→