On the Inability of Gaussian Process Regression to Optimally Learn Compositional Functions

Item #:

068431-1623

Details

DOI: https://doi.org/10.52202/068431-1623
Author(s): Matteo Giordano, Kolyan Ray, Johannes Schmidt-Hieber
Pages: 22341-22353 (13 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 35
Date/Location: Held 28 November - 9 December 2022, New Orleans, Louisiana, USA.
Series: Advances in Neural Information Processing Systems 35
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)

DOI: https://doi.org/10.52202/068431-1623
Author(s): Matteo Giordano, Kolyan Ray, Johannes Schmidt-Hieber
Pages: 22341-22353 (13 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 35
Date/Location: Held 28 November - 9 December 2022, New Orleans, Louisiana, USA.
Series: Advances in Neural Information Processing Systems 35
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)