Symmetry exploits for Bayesian cubature methods

DOI10.1007/S11222-019-09896-8zbMATH Open1435.62030arXiv1809.10227OpenAlexW2962817196WikidataQ127281544 ScholiaQ127281544MaRDI QIDQ2302452FDOQ2302452

Simo Särkkä, Toni Karvonen, Chris J. Oates

Publication date: 26 February 2020

Published in: Statistics and Computing (Search for Journal in Brave)

Abstract: Bayesian cubature provides a flexible framework for numerical integration, in which a priori knowledge on the integrand can be encoded and exploited. This additional flexibility, compared to many classical cubature methods, comes at a computational cost which is cubic in the number of evaluations of the integrand. It has been recently observed that fully symmetric point sets can be exploited in order to reduce - in some cases substantially - the computational cost of the standard Bayesian cubature method. This work identifies several additional symmetry exploits within the Bayesian cubature framework. In particular, we go beyond earlier work in considering non-symmetric measures and, in addition to the standard Bayesian cubature method, present exploits for the Bayes-Sard cubature method and the multi-output Bayesian cubature method.

Full work available at URL: https://arxiv.org/abs/1809.10227

zbMATH Keywords

Gaussian processesnumerical integrationprobabilistic numericsfully symmetric sets

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Bayesian inference (62F15) Probabilistic methods, stochastic differential equations (65C99) Numerical quadrature and cubature formulas (65D32)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Fully symmetric interpolatory rules for multiple integrals over infinite regions with Gaussian weight
• Fully Symmetric Interpolatory Rules for Multiple Integrals
• A sparse matrix arithmetic based on \({\mathfrak H}\)-matrices. I: Introduction to \({\mathfrak H}\)-matrices
• Probabilistic integration: a role in statistical computation?
• Sparse spectrum Gaussian process regression
• Kernels for vector-valued functions: a review
• A Hilbert Space Embedding for Distributions
• Probabilistic numerics and uncertainty in computations
• Compression, inversion, and approximate PCA of dense kernel matrices at near-linear computational complexity
• On the Equivalence between Kernel Quadrature Rules and Random Feature Expansions
• The concentration of measure phenomenon
• Scattered Data Approximation
• Bayes-Hermite quadrature
• Fast and Exact Simulation of Stationary Gaussian Processes through Circulant Embedding of the Covariance Matrix
• Modeling uncertainty in flow simulations via generalized polynomial chaos.
• Error estimates and condition numbers for radial basis function interpolation
• QMC designs: Optimal order Quasi Monte Carlo integration schemes on the sphere
• Uncertainty quantification in chemical systems
• Simple cubature formulas with high polynomial exactness
• Why Are High-Dimensional Finance Problems Often of Low Effective Dimension?
• Gaussian measure in Hilbert space and applications in numerical analysis
• Sparse grid quadrature in high dimensions with applications in finance and insurance
• Higher-Dimensional Integration with Gaussian Weight for Applications in Probabilistic Design
• Convergence analysis of deterministic kernel-based quadrature rules in misspecified settings
• Optimal Monte Carlo integration on closed manifolds
• Numerical cubature on scattered data by radial basis functions
• Construction of fully symmetric numerical integration formulas
• On an interpolatory method for high dimensional integration
• Gaussian kernel quadrature at scaled Gauss-Hermite nodes
• Computing a quantity of interest from observational data
• Fully Symmetric Kernel Quadrature
• Fast automatic Bayesian cubature using lattice sampling
• Bayesian Quadrature, Energy Minimization, and Space-Filling Design
• Efficient Quadrature Rules for Illumination Integrals: From Quasi Monte Carlo to Bayesian Monte Carlo

Cited In (5)

• Convergence analysis of deterministic kernel-based quadrature rules in misspecified settings
• A modern retrospective on probabilistic numerics
• Bayes-Hermite quadrature
• Adaptive experiment design for probabilistic integration
• A role for symmetry in the Bayesian solution of differential equations

Uses Software

• PATSYM
• HRMSYM

This page was built for publication: Symmetry exploits for Bayesian cubature methods

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2302452)