Stationary Kernels and Gaussian Processes on Lie Groups and their
Homogeneous Spaces I: the compact case
- URL: http://arxiv.org/abs/2208.14960v3
- Date: Tue, 7 Nov 2023 15:05:42 GMT
- Title: Stationary Kernels and Gaussian Processes on Lie Groups and their
Homogeneous Spaces I: the compact case
- Authors: Iskander Azangulov, Andrei Smolensky, Alexander Terenin, and
Viacheslav Borovitskiy
- Abstract summary: In to symmetries is one of the most fundamental forms of prior information one can consider.
In this work, we develop constructive and practical techniques for building stationary Gaussian processes on a very large class of non-Euclidean spaces.
- Score: 43.877478563933316
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Gaussian processes are arguably the most important class of spatiotemporal
models within machine learning. They encode prior information about the modeled
function and can be used for exact or approximate Bayesian learning. In many
applications, particularly in physical sciences and engineering, but also in
areas such as geostatistics and neuroscience, invariance to symmetries is one
of the most fundamental forms of prior information one can consider. The
invariance of a Gaussian process' covariance to such symmetries gives rise to
the most natural generalization of the concept of stationarity to such spaces.
In this work, we develop constructive and practical techniques for building
stationary Gaussian processes on a very large class of non-Euclidean spaces
arising in the context of symmetries. Our techniques make it possible to (i)
calculate covariance kernels and (ii) sample from prior and posterior Gaussian
processes defined on such spaces, both in a practical manner. This work is
split into two parts, each involving different technical considerations: part I
studies compact spaces, while part II studies non-compact spaces possessing
certain structure. Our contributions make the non-Euclidean Gaussian process
models we study compatible with well-understood computational techniques
available in standard Gaussian process software packages, thereby making them
accessible to practitioners.
Related papers
- Posterior Contraction Rates for Mat\'ern Gaussian Processes on
Riemannian Manifolds [51.68005047958965]
We show that intrinsic Gaussian processes can achieve better performance in practice.
Our work shows that finer-grained analyses are needed to distinguish between different levels of data-efficiency.
arXiv Detail & Related papers (2023-09-19T20:30:58Z) - Stationary Kernels and Gaussian Processes on Lie Groups and their Homogeneous Spaces II: non-compact symmetric spaces [43.877478563933316]
In to symmetries is one of the most fundamental forms of prior information one can consider.
In this work, we develop constructive and practical techniques for building stationary Gaussian processes on a very large class of non-Euclidean spaces.
arXiv Detail & Related papers (2023-01-30T17:27:12Z) - Gaussian Processes and Statistical Decision-making in Non-Euclidean
Spaces [96.53463532832939]
We develop techniques for broadening the applicability of Gaussian processes.
We introduce a wide class of efficient approximations built from this viewpoint.
We develop a collection of Gaussian process models over non-Euclidean spaces.
arXiv Detail & Related papers (2022-02-22T01:42:57Z) - Vector-valued Gaussian Processes on Riemannian Manifolds via Gauge
Equivariant Projected Kernels [108.60991563944351]
We present a recipe for constructing gauge equivariant kernels, which induce vector-valued Gaussian processes coherent with geometry.
We extend standard Gaussian process training methods, such as variational inference, to this setting.
arXiv Detail & Related papers (2021-10-27T13:31:10Z) - Advanced Stationary and Non-Stationary Kernel Designs for Domain-Aware
Gaussian Processes [0.0]
We propose advanced kernel designs that only allow for functions with certain desirable characteristics to be elements of the reproducing kernel Hilbert space (RKHS)
We will show the impact of advanced kernel designs on Gaussian processes using several synthetic and two scientific data sets.
arXiv Detail & Related papers (2021-02-05T22:07:56Z) - Mat\'ern Gaussian processes on Riemannian manifolds [81.15349473870816]
We show how to generalize the widely-used Mat'ern class of Gaussian processes.
We also extend the generalization from the Mat'ern to the widely-used squared exponential process.
arXiv Detail & Related papers (2020-06-17T21:05:42Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.