Sample Path Regularity of Gaussian Processes from the Covariance Kernel
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911351062921216 |
|---|---|
| author | Da Costa, Nathaël Pförtner, Marvin Da Costa, Lancelot Hennig, Philipp |
| author_facet | Da Costa, Nathaël Pförtner, Marvin Da Costa, Lancelot Hennig, Philipp |
| contents | Gaussian processes (GPs) are the most common formalism for defining probability distributions over spaces of functions. While applications of GPs are myriad, a comprehensive understanding of GP sample paths, i.e. the function spaces over which they define a probability measure, is lacking. In practice, GPs are not constructed through a probability measure, but instead through a mean function and a covariance kernel. In this paper we provide necessary and sufficient conditions on the covariance kernel for the sample paths of the corresponding GP to attain a given regularity. We focus primarily on Hölder regularity as it grants particularly straightforward conditions, which simplify further in the cases of stationary and isotropic GPs. We then demonstrate that our results allow for novel and unusually tight characterisations of the sample path regularities of the GPs commonly used in machine learning applications, such as the Matérn GPs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_14886 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Sample Path Regularity of Gaussian Processes from the Covariance Kernel Da Costa, Nathaël Pförtner, Marvin Da Costa, Lancelot Hennig, Philipp Machine Learning Probability Statistics Theory Gaussian processes (GPs) are the most common formalism for defining probability distributions over spaces of functions. While applications of GPs are myriad, a comprehensive understanding of GP sample paths, i.e. the function spaces over which they define a probability measure, is lacking. In practice, GPs are not constructed through a probability measure, but instead through a mean function and a covariance kernel. In this paper we provide necessary and sufficient conditions on the covariance kernel for the sample paths of the corresponding GP to attain a given regularity. We focus primarily on Hölder regularity as it grants particularly straightforward conditions, which simplify further in the cases of stationary and isotropic GPs. We then demonstrate that our results allow for novel and unusually tight characterisations of the sample path regularities of the GPs commonly used in machine learning applications, such as the Matérn GPs. |
| title | Sample Path Regularity of Gaussian Processes from the Covariance Kernel |
| topic | Machine Learning Probability Statistics Theory |
| url | https://arxiv.org/abs/2312.14886 |