Stein variational gradient descent on infinite-dimensional space and applications to statistical inverse problems
arXiv:2102.09741 · doi:10.1137/21M1440773
Abstract
In this paper, we propose an infinite-dimensional version of the Stein variational gradient descent (iSVGD) method for solving Bayesian inverse problems. The method can generate approximate samples from posteriors efficiently. Based on the concepts of operator-valued kernels and vector-valued reproducing kernel Hilbert spaces, a rigorous definition is given for the infinite-dimensional objects, e.g., the Stein operator, which are proved to be the limit of finite-dimensional ones. Moreover, a more efficient iSVGD with preconditioning operators is constructed by generalizing the change of variables formula and introducing a regularity parameter. The proposed algorithms are applied to an inverse problem of the steady state Darcy flow equation. Numerical results confirm our theoretical findings and demonstrate the potential applications of the proposed approach in the posterior sampling of large-scale nonlinear statistical inverse problems.
arXiv comment28 pages
References in corpus (15)
- Dimension-independent likelihood-informed MCMC
- Functional Variational Bayesian Neural Networks
- Convergence and Concentration of Empirical Measures under Wasserstein Distance in Unbounded Functional Spaces
- Posterior Contraction Rates for the Bayesian Approach to Linear Ill-Posed Inverse Problems
- Maximum-A-Posteriori Estimates in Linear Inverse Problems with Log-concave Priors are Proper Bayes Estimators
- Kullback-Leibler Approximation for Probability Measures on Infinite Dimensional Spaces
- Stein Variational Gradient Descent With Matrix-Valued Kernels
- A Stein variational Newton method
- Projected Stein Variational Newton: A Fast and Scalable Bayesian Inference Method in High Dimensions
- A variational Bayesian method for inverse problems with impulsive noise
- Hessian metric via transport information geometry
- Variational Bayes' method for functions with applications to some inverse problems
- Infinite-dimensional Bayesian approach for inverse scattering problems of a fractional Helmholtz equation
- Recursive linearization method for inverse medium scattering problems with complex mixture Gaussian error learning
- Posterior contraction for empirical Bayesian approach to inverse problems under non-diagonal assumption