Reproducing kernel Hilbert spaces of Gaussian priors

Abstract

We review definitions and properties of reproducing kernel Hilbert spaces attached to Gaussian variables and processes, with a view to applications in nonparametric Bayesian statistics using Gaussian priors. The rate of contraction of posterior distributions based on Gaussian priors can be described through a concentration function that is expressed in the reproducing Hilbert space. Absolute continuity of Gaussian measures and concentration inequalities play an important role in understanding and deriving this result. Series expansions of Gaussian variables and transformations of their reproducing kernel Hilbert spaces under linear maps are useful tools to compute the concentration function.

Published in at http://dx.doi.org/10.1214/074921708000000156 the IMS Collections (http://www.imstat.org/publications/imscollections.htm) by the Institute of Mathematical Statistics (http://www.imstat.org)

References in corpus (1)

• Rates of contraction of posterior distributions based on Gaussian process priors

Cited by in corpus (51)

• Rates of contraction of posterior distributions based on Gaussian process priors
• Convergence rates of efficient global optimization algorithms
• Adaptive Bayesian estimation using a Gaussian random field with inverse Gamma bandwidth
• Bayesian inverse problems with Gaussian priors
• Gaussian Processes and Kernel Methods: A Review on Connections and Equivalences
• On the Bernstein-von Mises phenomenon for nonparametric Bayes procedures
• Confidence Intervals for Projections of Partially Identified Parameters
• Nonparametric Bernstein-von Mises theorems in Gaussian white noise
• On Bayesian supremum norm contraction rates
• A Bernstein-von Mises theorem for smooth functionals in semiparametric models
• Learning Differential Equations that are Easy to Solve
• Bayesian inverse problems with non-conjugate priors
• Bayesian inference with rescaled Gaussian process priors
• Rates of contraction for posterior distributions in $\bolds{L^r}$-metrics, $\bolds{1\le r\le\infty}$
• Minimax-optimal nonparametric regression in high dimensions
• Anisotropic function estimation using multi-bandwidth Gaussian processes
• Lower bounds for posterior rates with Gaussian process priors
• Adaptive nonparametric Bayesian inference using location-scale mixture priors
• Gaussian process methods for one-dimensional diffusions: optimal rates and adaptation
• Bayesian Nonparametric Causal Inference: Information Rates and Learning Algorithms
• Bayes factor consistency
• Semiparametric Bayesian causal inference
• On the existence of paths between points in high level excursion sets of Gaussian random fields
• Convergence Guarantees for Gaussian Process Means With Misspecified Likelihoods and Smoothness
• Optimality of Poisson processes intensity learning with Gaussian processes
• Comparing and weighting imperfect models using D-probabilities
• Optimal Bayesian estimation in random covariate design with a rescaled Gaussian process prior
• Asymptotic equivalence for regression under fractional noise
• Bayesian Manifold Regression
• Modeling Dynamic Functional Connectivity with Latent Factor Gaussian Processes
• Unlabeled Data Help in Graph-Based Semi-Supervised Learning: A Bayesian Nonparametrics Perspective
• Hanson-Wright inequality in Hilbert spaces with application to $K$-means clustering for non-Euclidean data
• Graph Based Gaussian Processes on Restricted Domains
• Dimension-free convergence rates for gradient Langevin dynamics in RKHS
• Adaptive inference over Besov spaces in the white noise model using $p$-exponential priors
• An RKHS Approach to Estimation with Sparsity Constraints
• Comparing Scale Parameter Estimators for Gaussian Process Interpolation with the Brownian Motion Prior: Leave-One-Out Cross Validation and Maximum Likelihood
• Finite Element Representations of Gaussian Processes: Balancing Numerical and Statistical Accuracy
• Convergence of Gaussian process regression: Optimality, robustness, and relationship with kernel ridge regression
• Kriging prediction with isotropic Matérn correlations: Robustness and experimental design
• Bayesian hierarchical modeling of simply connected 2D shapes
• Full adaptation to smoothness using randomly truncated series priors with Gaussian coefficients and inverse gamma scaling
• Posterior Consistency via Precision Operators for Bayesian Nonparametric Drift Estimation in SDEs
• Posterior contraction rates for constrained deep Gaussian processes in density estimation and classication
• Gaussian Approximation of General Nonparametric Posterior Distributions
• Posterior contraction for deep Gaussian process priors
• Large deviations for local times and intersection local times of fractional Brownian motions and Riemann-Liouville processes
• Semi-parametric Bernstein-von Mises in Linear Inverse Problems
• Quasi-Bayesian Dual Instrumental Variable Regression
• Thomas Bayes' walk on manifolds
• On the Convergence of Bayesian Regression Models