Fast variable selection makes scalable Gaussian process BSS-ANOVA a speedy and accurate choice for tabular and time series regression. (arXiv:2205.13676v1 [cs.LG])

Gaussian processes (GPs) are non-parametric regression engines with a long
history. They are often overlooked in modern machine learning contexts because
of scalability issues: regression for traditional GP kernels are
$\mathcal{O}(N^3)$ where $N$ is the size of the dataset. One of a number of
scalable GP approaches is the Karhunen-Lo\'eve (KL) decomposed kernel
BSS-ANOVA, developed in 2009. It is $\mathcal{O}(NP)$ in training and
$\mathcal{O}(P)$ per point in prediction, where $P$ is the number of terms in
the ANOVA / KL …

anova arxiv bss process regression scalable series tabular time time series