Randomized maximum likelihood based posterior sampling
From MaRDI portal
Abstract: Minimization of a stochastic cost function is commonly used for approximate sampling in high-dimensional Bayesian inverse problems with Gaussian prior distributions and multimodal posterior distributions. The density of the samples generated by minimization is not the desired target density, unless the observation operator is linear, but the distribution of samples is useful as a proposal density for importance sampling or for Markov chain Monte Carlo methods. In this paper, we focus on applications to sampling from multimodal posterior distributions in high dimensions. We first show that sampling from multimodal distributions is improved by computing all critical points instead of only minimizers of the objective function. For applications to high-dimensional geoscience problems, we demonstrate an efficient approximate weighting that uses a low-rank Gauss-Newton approximation of the determinant of the Jacobian. The method is applied to two toy problems with known posterior distributions and a Darcy flow problem with multiple modes in the posterior.
Recommendations
- Computing Marginal Likelihoods via Posterior Sampling
- A random weighting approach for posterior distributions
- Marginal maximum a posteriori estimation using Markov chain Monte Carlo
- Posterior inference in the random intercept model based on samples obtained with Markov chain Monte Carlo methods
- Posterior sampling from -approximation of normalized completely random measure mixtures
- Posterior sampling when the normalizing constant is unknown
Cites work
- scientific article; zbMATH DE number 2061729 (Why is no real title available?)
- scientific article; zbMATH DE number 849927 (Why is no real title available?)
- A Randomized Maximum A Posteriori Method for Posterior Sampling of High Dimensional Nonlinear Bayesian Inverse Problems
- A computational framework for infinite-dimensional Bayesian inverse problems. I: The linearized case, with application to global seismic inversion
- A stochastic Newton MCMC method for large-scale statistical inverse problems with application to seismic inversion
- Adaptive proposal distribution for random walk Metropolis algorithm
- An adaptive Metropolis algorithm
- An analysis of history matching errors
- Automated solution of differential equations by the finite element method. The FEniCS book
- Curse-of-dimensionality revisited: Collapse of the particle filter in very large scale systems
- Data assimilation in truncated plurigaussian models: impact of the truncation map
- Dimension-independent likelihood-informed MCMC
- Inverse Problem Theory and Methods for Model Parameter Estimation
- MCMC-driven adaptive multiple importance sampling
- Metropolized randomized maximum likelihood for improved sampling from multimodal distributions
- On the stability of sequential Monte Carlo methods in high dimensions
- Preconditioning Markov Chain Monte Carlo Simulations Using Coarse-Scale Models
- Randomize-then-optimize: a method for sampling from posterior distributions in nonlinear inverse problems
- Recent progress on reservoir history matching: a review
- Scalable Optimization-Based Sampling on Function Space
- Solving PDEs in Python. The FEniCS tutorial I
- Variance reduction using nonreversible Langevin samplers
- \texttt{PETSc TSAdjoint}: a discrete adjoint ODE solver for first-order and second-order sensitivity analysis
- hIPPYlib
Cited in
(14)- Multi-domain sampling with applications to structural inference of Bayesian networks
- scientific article; zbMATH DE number 7307488 (Why is no real title available?)
- Metropolized randomized maximum likelihood for improved sampling from multimodal distributions
- Consensus‐based sampling
- Learning physics-based models from data: perspectives from inverse problems and model reduction
- Continuous Time Limit of the Stochastic Ensemble Kalman Inversion: Strong Convergence Analysis
- scientific article; zbMATH DE number 7219341 (Why is no real title available?)
- Computing Marginal Likelihoods via Posterior Sampling
- Hybrid iterative ensemble smoother for history matching of hierarchical models
- Minimization for conditional simulation: relationship to optimal transport
- An adaptive importance sampling algorithm for Bayesian inversion with multimodal distributions
- Randomize-then-optimize: a method for sampling from posterior distributions in nonlinear inverse problems
- A modified randomized maximum likelihood for improved Bayesian history matching
- Posterior simulation via the signed root log-likelihood ratio
This page was built for publication: Randomized maximum likelihood based posterior sampling
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2130957)
