Stein Variational Gradient Descent on Infinite-Dimensional Space and Applications to Statistical Inverse Problems

DOI10.1137/21M1440773zbMath1502.65044arXiv2102.09741OpenAlexW3130552779MaRDI QIDQ5102236

No author found.

Publication date: 6 September 2022

Published in: SIAM Journal on Numerical Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2102.09741

zbMATH Keywords

machine learningstatistical inverse problemsStein variational gradient descentBayes' methodvariational inference method

Mathematics Subject Classification ID

Bayesian inference (62F15) Inverse problems in optimal control (49N45) Numerical solution of inverse problems involving ordinary differential equations (65L09)

Related Items (1)

A Bayesian scheme for reconstructing obstacles in acoustic waveguides

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• FEM-based discretization-invariant MCMC methods for PDE-constrained Bayesian inverse problems
• A variational Bayesian method to inverse problems with impulsive noise
• Kolmogorov equations for stochastic PDEs.
• Automated solution of differential equations by the finite element method. The FEniCS book
• Bernstein-von Mises theorems for statistical inverse problems. I: Schrödinger equation
• Infinite-dimensional Bayesian approach for inverse scattering problems of a fractional Helmholtz equation
• Statistical and computational inverse problems.
• Posterior contraction for empirical Bayesian approach to inverse problems under non-diagonal assumption
• Accelerated information gradient flow
• Convergence and concentration of empirical measures under Wasserstein distance in unbounded functional spaces
• A variational Bayesian approach for inverse problems with skew-\(t\) error distributions
• Dimension-independent likelihood-informed MCMC
• Functional data analysis.
• An introduction to infinite-dimensional analysis
• Hierarchical Bayesian inference for ill-posed problems via variational method
• Inverse problems: A Bayesian perspective
• Numerical PDE-Constrained Optimization
• Maximuma posterioriestimates in linear inverse problems with log-concave priors are proper Bayes estimators
• A Randomized Maximum A Posteriori Method for Posterior Sampling of High Dimensional Nonlinear Bayesian Inverse Problems
• VECTOR VALUED REPRODUCING KERNEL HILBERT SPACES AND UNIVERSALITY
• VECTOR VALUED REPRODUCING KERNEL HILBERT SPACES OF INTEGRABLE FUNCTIONS AND MERCER THEOREM
• Maximuma posterioriprobability estimates in infinite-dimensional Bayesian inverse problems
• Kullback--Leibler Approximation for Probability Measures on Infinite Dimensional Spaces
• Optimal Low-rank Approximations of Bayesian Linear Inverse Problems
• Algorithms for Kullback--Leibler Approximation of Probability Measures in Infinite Dimensions
• On the Rate of Convergence of Empirical Measures in ∞-transportation Distance
• Bayesian inverse problems for functions and applications to fluid mechanics
• Scaling Limit of the Stein Variational Gradient Descent: The Mean Field Regime
• An Adaptive Independence Sampler MCMC Algorithm for Bayesian Inferences of Functions
• Inverse Problem Theory and Methods for Model Parameter Estimation
• Recursive linearization method for inverse medium scattering problems with complex mixture Gaussian error learning
• Stein Variational Reduced Basis Bayesian Inversion
• Bayesian Inference and Uncertainty Quantification for Medical Image Reconstruction with Poisson Data
• Interacting Langevin Diffusions: Gradient Structure and Ensemble Kalman Sampler
• Solving inverse problems using data-driven models
• A Computational Framework for Infinite-Dimensional Bayesian Inverse Problems Part I: The Linearized Case, with Application to Global Seismic Inversion
• Variational Bayes' Method for Functions with Applications to Some Inverse Problems
• Hessian metric via transport information geometry
• Sequential Monte Carlo methods for Bayesian elliptic inverse problems
• MCMC methods for functions: modifying old algorithms to make them faster
• Stochastic Equations in Infinite Dimensions

This page was built for publication: Stein Variational Gradient Descent on Infinite-Dimensional Space and Applications to Statistical Inverse Problems