Spectral Bayesian Regression on the Sphere

TL;DR

This paper introduces a Bayesian nonparametric regression method on the sphere using harmonic analysis, providing exact posterior formulas, optimal spectral truncation, and minimax contraction rates for spherical data.

Contribution

It develops an intrinsic Bayesian framework for spherical regression with explicit spectral and posterior analysis, including optimal truncation and contraction rate results.

Findings

Exact posterior distributions derived for spherical harmonic coefficients.

Optimal spectral truncation schemes established for Bayesian regression.

Posterior contraction rates shown to be minimax-optimal under certain priors.

Abstract

We develop a fully intrinsic Bayesian framework for nonparametric regression on the unit sphere based on isotropic Gaussian field priors and the harmonic structure induced by the Laplace-Beltrami operator. Under uniform random design, the regression model admits an exact diagonalization in the spherical harmonic basis, yielding a Gaussian sequence representation with frequency-dependent multiplicities. Exploiting this structure, we derive closed-form posterior distributions, optimal spectral truncation schemes, and sharp posterior contraction rates under integrated squared loss. For Gaussian priors with polynomially decaying angular power spectra, including spherical Mat\'ern priors, we establish posterior contraction rates over Sobolev classes, which are minimax-optimal under correct prior calibration. We further show that the posterior mean admits an exact variational characterization as a geometrically intrinsic penalized least-squares estimator, equivalent to a Laplace-Beltrami smoothing spline.