Fast variable selection makes Karhunen-Lo\`eve decomposed Gaussian process BSS-ANOVA a speedy and accurate choice for dynamic systems identification. (arXiv:2205.13676v2 [cs.LG] UPDATED)

Many approaches for scalable GPs have focused on using a subset of data as
inducing points. Another promising approach is the Karhunen-Lo\`eve (KL)
decomposition, in which the GP kernel is represented by a set of basis
functions which are the eigenfunctions of the kernel operator. Such kernels
have the potential to be very fast, and do not depend on the selection of a
reduced set of inducing points. However KL decompositions lead to high
dimensionality, and variable selection thus becomes …

anova arxiv bss identification lg process systems