On the inability of Gaussian process regression to optimally learn compositional functions

This is a publication. If there is no link to the publication on this page, you can try the pre-formated search via the search engines listed on this page.

Authors: Matteo Giordano, Johannes Schmidt-Hieber, Kolyan Ra

Journal title: Advances in Neural Information Processing Systems 36

Journal number: 10495258

Journal publisher: NeurIPS

Published year: 2022

DOI identifier: 10.48550/arxiv.2205.07764

ISSN: 1049-5258