Practical Hilbert space approximate Bayesian Gaussian processes for probabilistic programming
From MaRDI portal
Abstract: Gaussian processes are powerful non-parametric probabilistic models for stochastic functions. However, the direct implementation entails a complexity that is computationally intractable when the number of observations is large, especially when estimated with fully Bayesian methods such as Markov chain Monte Carlo. In this paper, we focus on a low-rank approximate Bayesian Gaussian processes, based on a basis function approximation via Laplace eigenfunctions for stationary covariance functions. The main contribution of this paper is a detailed analysis of the performance, and practical recommendations for how to select the number of basis functions and the boundary factor. Intuitive visualizations and recommendations, make it easier for users to improve approximation accuracy and computational performance. We also propose diagnostics for checking that the number of basis functions and the boundary factor are adequate given the data. The approach is simple and exhibits an attractive computational complexity due to its linear structure, and it is easy to implement in probabilistic programming frameworks. Several illustrative examples of the performance and applicability of the method in the probabilistic programming language Stan are presented together with the underlying Stan model code.
Recommendations
- Hilbert space methods for reduced-rank Gaussian process regression
- scientific article; zbMATH DE number 6276239
- Approximations for binary Gaussian process classification
- Adaptive Gaussian Process Approximation for Bayesian Inference with Expensive Likelihood Functions
- Assessing approximate inference for binary Gaussian process classification.
Cites work
- scientific article; zbMATH DE number 3751955 (Why is no real title available?)
- scientific article; zbMATH DE number 45848 (Why is no real title available?)
- scientific article; zbMATH DE number 3560401 (Why is no real title available?)
- scientific article; zbMATH DE number 3797051 (Why is no real title available?)
- scientific article; zbMATH DE number 876688 (Why is no real title available?)
- scientific article; zbMATH DE number 3259552 (Why is no real title available?)
- scientific article; zbMATH DE number 3273551 (Why is no real title available?)
- scientific article; zbMATH DE number 3320868 (Why is no real title available?)
- A framework to understand the asymptotic properties of kriging and splines
- A survey of Bayesian predictive methods for model assessment, selection and comparison
- A unifying view of sparse approximate Gaussian process regression
- Bayesian data analysis.
- Bayesian inference for spatio-temporal spike-and-slab priors
- GPflow: a Gaussian process library using TensorFlow
- GPstuff: Bayesian modeling with Gaussian processes
- Gaussian processes for machine learning (GPML) toolbox
- Gaussian processes for machine learning.
- Handbook of Markov Chain Monte Carlo
- Hierarchical modeling and analysis for spatial data
- Hilbert space methods for reduced-rank Gaussian process regression
- Practical Bayesian model evaluation using leave-one-out cross-validation and WAIC
- Probabilistic integration: a role in statistical computation?
- Probabilistic numerics and uncertainty in computations
- Regression and other stories
- Sparse spectrum Gaussian process regression
- Statistical analysis of spatial and spatio-temporal point patterns
- Variational Fourier features for Gaussian processes
Cited in
(7)- Sequential Kalman tuning of the \(t\)-preconditioned Crank-Nicolson algorithm: efficient, adaptive and gradient-free inference for Bayesian inverse problems
- Detecting and diagnosing prior and likelihood sensitivity with power-scaling
- A scalable approximate Bayesian inference for high-dimensional Gaussian processes
- Hilbert space methods for reduced-rank Gaussian process regression
- A fully Bayesian sparse polynomial chaos expansion approach with joint priors on the coefficients and global selection of terms
- rts2
- Scalable Computation of Predictive Probabilities in Probit Models with Gaussian Process Priors
Describes a project that uses
Uses Software
This page was built for publication: Practical Hilbert space approximate Bayesian Gaussian processes for probabilistic programming
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q91882)
