[2506.17366] Gaussian Processes and Reproducing Kernel Hilbert Spaces: Connections and Equivalences
Abstract:This monograph studies the relations between two approaches using positive definite kernels: probabilistic methods using Gaussian processes, and non-probabilistic methods using reproducing kernel Hilbert spaces (RKHS). They are widely studied and used in machine learning, statistics, and numerical analysis. We study connections and equivalences for fundamental topics such as regression, interpolation, numerical integration, distributional discrepancies, and statistical dependence, as well as sample path properties of Gaussian processes. A unifying perspective for these equivalences is established, based on the equivalence between the Gaussian Hilbert space and the RKHS. The monograph serves as a basis to bridge many other methods based on Gaussian processes and reproducing kernels, which are developed in parallel by the two research communities.
Gaussian Processes and Reproducing Kernel Hilbert Spaces: Connections and Equivalences Motonobu Kanagawa arXiv:2506.17366v3 [stat.ML] 9 Sep 2026 EURECOM motonobu.kanagawa@eurecom.fr Philipp Hennig University of Tübingen, Tübingen AI…
saved by
related reading
- rakhlin_mathstat_sp24.pdfmit.edu
- [2403.14606] The Elements of Differentiable Programmingarxiv.org
- Geometry of random sections of isotropic convex bodiesarxiv.org
- [2007.12826] The Interpolation Phase Transition in Neural Networks: Memorization and Generalization under Lazy Trainingarxiv.org
- An optimization perspective on log-concave sampling and beyond | Sinho Chewichewisinho.github.io
- [2605.01172] A Theory of Generalization in Deep Learningarxiv.org
- Pen and Paper Exercises in Machine Learningarxiv.org
- notes.pdfjingbol.web.illinois.edu
- High-Dimensional Gaussian Sampling: A Review and a Unifying Approach Based on a Stochastic Proximal Point Algorithmarxiv.org
- An Introduction to Malliavin Calculusuni-ulm.de
- A Visual Exploration of Gaussian Processesdistill.pub
- 0907.4178arxiv.org