Non-asymptotic error estimates for the Laplace approximation in Bayesian inverse problems

DOI10.1007/s00211-021-01266-9OpenAlexW3112621191MaRDI QIDQ2117305

Remo Kretschmann, Tapio Helin

Publication date: 21 March 2022

Published in: Numerische Mathematik (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2012.06603

Mathematics Subject Classification ID

Asymptotic distribution theory in statistics (62E20) Bayesian inference (62F15) Nonlinear ill-posed problems (47J06) Approximations to statistical distributions (nonasymptotic) (62E17) Numerical quadrature and cubature formulas (65D32) Numerical solutions of ill-posed problems in abstract spaces; regularization (65J20) Numerical integration (65D30) Numerical solution to inverse problems in abstract spaces (65J22)

Related Items (5)

Learning physics-based models from data: perspectives from inverse problems and model reduction ⋮ Small-noise approximation for Bayesian optimal experimental design with nuisance uncertainty ⋮ Dimension Free Nonasymptotic Bounds on the Accuracy of High-Dimensional Laplace Approximation ⋮ Re-thinking high-dimensional mathematical statistics. Abstracts from the workshop held May 15--21, 2022 ⋮ Foundations of Bayesian inference for complex statistical models. Abstracts from the workshop held May 2--8, 2021 (hybrid meeting)

Uses Software

• PRMLT

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• An explicit formula for the coefficients in Laplace's method
• Simple upper and lower bounds for the multivariate Laplace approximation
• Probability in Banach spaces. Isoperimetry and processes
• Efficient nonparametric Bayesian inference for \(X\)-ray transforms
• Bernstein-von Mises theorems for statistical inverse problems. I: Schrödinger equation
• Error bounds for multidimensional Laplace approximation
• Statistical and computational inverse problems.
• On the convergence of the Laplace approximation and noise-level-robustness of Laplace-based Monte Carlo methods for Bayesian inverse problems
• Hessian-based adaptive sparse quadrature for infinite-dimensional Bayesian inverse problems
• Fast Bayesian experimental design: Laplace-based importance sampling for the expected information gain
• Multivariate Laplace's approximation with estimated error and application to limit theorems
• Fast estimation of expected information gains for Bayesian experimental designs based on Laplace approximations
• Error bounds for the Laplace approximation for definite integrals
• Asymptotic Approximations of Integrals
• Inverse problems: A Bayesian perspective
• Approximate Bayesian Inference for Latent Gaussian models by using Integrated Nested Laplace Approximations
• Introduction to Uncertainty Quantification
• Scaling limits in computational Bayesian inversion
• A Fast and Scalable Method for A-Optimal Design of Experiments for Infinite-dimensional Bayesian Nonlinear Inverse Problems
• Asymptotic Statistics
• On Choosing and Bounding Probability Metrics
• Bernstein--von Mises Theorems and Uncertainty Quantification for Linear Inverse Problems
• Data Assimilation
• A Review of Modern Computational Algorithms for Bayesian Optimal Design

This page was built for publication: Non-asymptotic error estimates for the Laplace approximation in Bayesian inverse problems