Unbiased Stochastic Optimization for Gaussian Processes on Finite Dimensional RKHS

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shoham, Neta, Avron, Haim
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915467949506560
author Shoham, Neta
Avron, Haim
author_facet Shoham, Neta
Avron, Haim
contents Current methods for stochastic hyperparameter learning in Gaussian Processes (GPs) rely on approximations, such as computing biased stochastic gradients or using inducing points in stochastic variational inference. However, when using such methods we are not guaranteed to converge to a stationary point of the true marginal likelihood. In this work, we propose algorithms for exact stochastic inference of GPs with kernels that induce a Reproducing Kernel Hilbert Space (RKHS) of moderate finite dimension. Our approach can also be extended to infinite dimensional RKHSs at the cost of forgoing exactness. Both for finite and infinite dimensional RKHSs, our method achieves better experimental results than existing methods when memory resources limit the feasible batch size and the possible number of inducing points.
format Preprint
id arxiv_https___arxiv_org_abs_2508_20588
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unbiased Stochastic Optimization for Gaussian Processes on Finite Dimensional RKHS
Shoham, Neta
Avron, Haim
Machine Learning
Current methods for stochastic hyperparameter learning in Gaussian Processes (GPs) rely on approximations, such as computing biased stochastic gradients or using inducing points in stochastic variational inference. However, when using such methods we are not guaranteed to converge to a stationary point of the true marginal likelihood. In this work, we propose algorithms for exact stochastic inference of GPs with kernels that induce a Reproducing Kernel Hilbert Space (RKHS) of moderate finite dimension. Our approach can also be extended to infinite dimensional RKHSs at the cost of forgoing exactness. Both for finite and infinite dimensional RKHSs, our method achieves better experimental results than existing methods when memory resources limit the feasible batch size and the possible number of inducing points.
title Unbiased Stochastic Optimization for Gaussian Processes on Finite Dimensional RKHS
topic Machine Learning
url https://arxiv.org/abs/2508.20588