• Corpus ID: 237592970

Contraction rates for sparse variational approximations in Gaussian process regression

  title={Contraction rates for sparse variational approximations in Gaussian process regression},
  author={Dennis Nieman and Botond Szab{\'o} and Harry van Zanten},
We study the theoretical properties of a variational Bayes method in the Gaussian Process regression model. We consider the inducing variables method introduced by Titsias (2009b) and derive sufficient conditions for obtaining contraction rates for the corresponding variational Bayes (VB) posterior. As examples we show that for three particular covariance kernels (Matérn, squared exponential, random series prior) the VB approach can achieve optimal, minimax contraction rates for a sufficiently… 

Figures and Tables from this paper

Posterior contraction for deep Gaussian process priors

It is shown that the contraction rates can achieve the minimax convergence rate (up to log n factors), while being adaptive to the underlying structure and smoothness of the target function.

Improved Convergence Rates for Sparse Approximation Methods in Kernel-Based Learning

Novel confidence intervals are provided for the Nyström method and the sparse variational Gaussian process approximation method, which are established using novel interpretations of the approximate (surrogate) posterior variance of the models.

Optimal recovery and uncertainty quantification for distributed Gaussian process regression

This work derives frequentist theoretical guarantees and limitations for a range of distributed methods for general GP priors in context of the nonparametric regression model, both for recovery and uncertainty quantification.

Ultra-fast Deep Mixtures of Gaussian Process Experts

This article proposes to design the gating network for selecting the experts from such mixtures of sparse GPs using a deep neural network (DNN) which provides a flexible, robust, and efficient model which is able to significantly outperform competing models.



Variational Model Selection for Sparse Gaussian Process Regression

A variational formulation for sparse approximations that jointly infers the inducing inputs and the kernel hyperparameters by maximizing a lower bound of the true log marginal likelihood.

Variational Learning of Inducing Variables in Sparse Gaussian Processes

A variational formulation for sparse approximations that jointly infers the inducing inputs and the kernel hyperparameters by maximizing a lower bound of the true log marginal likelihood.

Rates of contraction of posterior distributions based on Gaussian process priors

The rate of contraction of the posterior distribution based on sampling from a smooth density model when the prior models the log density as a (fractionally integrated) Brownian motion is shown to depend on the position of the true parameter relative to the reproducing kernel Hilbert space of the Gaussian process.

Variational Bayes for High-Dimensional Linear Regression With Sparse Priors

A mean-field spike and slab variational Bayes (VB) approximation to Bayesian model selection priors in sparse high-dimensional linear regression is studied, showing that it works comparably well as other state-of-the-art Bayesian variable selection methods.

Variational Fourier Features for Gaussian Processes

This work hinges on a key result that there exist spectral features related to a finite domain of the Gaussian process which exhibit almost-independent covariances, and derives these expressions for Matern kernels in one dimension, and generalize to more dimensions using kernels with specific structures.

Information Rates of Nonparametric Gaussian Process Methods

The results show that for good performance, the regularity of the GP prior should match the regularities of the unknown response function, and is expressible in a certain concentration function.

On Sparse Variational Methods and the Kullback-Leibler Divergence between Stochastic Processes

A substantial generalization of the literature on variational framework for learning inducing variables is given and a new proof of the result for infinite index sets is given which allows inducing points that are not data points and likelihoods that depend on all function values.

Convergence of Sparse Variational Inference in Gaussian Processes Regression

It is shown that the KL-divergence between the approximate model and the exact posterior arbitrarily small for a Gaussian-noise regression model with M needs to grow with N to ensure high quality approximations.

Rates of Convergence for Sparse Variational Gaussian Process Regression

The results show that as datasets grow, Gaussian process posteriors can truly be approximated cheaply, and provide a concrete rule for how to increase $M$ in continual learning scenarios.

Reproducing kernel Hilbert spaces of Gaussian priors

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