Skip to Main content Skip to Navigation
Conference papers

Numerical issues in maximum likelihood parameter estimation for Gaussian process interpolation

Abstract : This article investigates the origin of numerical issues in maximum likelihood parameter estimation for Gaussian process (GP) interpolation and investigates simple but effective strategies for improving commonly used open-source software implementations. This work targets a basic problem but a host of studies, particularly in the literature of Bayesian optimization, rely on off-the-shelf GP implementations. For the conclusions of these studies to be reliable and reproducible, robust GP implementations are critical.
Complete list of metadata

https://hal-centralesupelec.archives-ouvertes.fr/hal-03119528
Contributor : Emmanuel Vazquez <>
Submitted on : Wednesday, July 28, 2021 - 3:47:05 PM
Last modification on : Monday, August 2, 2021 - 9:34:32 AM

File

saferGPMLE-paper.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution - NonCommercial - NoDerivatives 4.0 International License

Identifiers

  • HAL Id : hal-03119528, version 2
  • ARXIV : 2101.09747

Citation

Subhasish Basak, Sébastien Petit, Julien Bect, Emmanuel Vazquez. Numerical issues in maximum likelihood parameter estimation for Gaussian process interpolation. 7th International Conference on machine Learning, Optimization and Data science (LOD 2021), Oct 2021, Grasmere, United Kingdom. ⟨hal-03119528v2⟩

Share

Metrics

Record views

8