Dimension-independent likelihood-informed MCMC
From MaRDI portal
Publication:2374891
DOI10.1016/J.JCP.2015.10.008zbMATH Open1349.65009arXiv1411.3688OpenAlexW2142737094MaRDI QIDQ2374891FDOQ2374891
Authors: Tiangang Cui, K. J. H. Law, Youssef M. Marzouk 
Publication date: 5 December 2016
Published in: Journal of Computational Physics (Search for Journal in Brave)
Abstract: Many Bayesian inference problems require exploring the posterior distribution of high-dimensional parameters that represent the discretization of an underlying function. This work introduces a family of Markov chain Monte Carlo (MCMC) samplers that can adapt to the particular structure of a posterior distribution over functions. Two distinct lines of research intersect in the methods developed here. First, we introduce a general class of operator-weighted proposal distributions that are well defined on function space, such that the performance of the resulting MCMC samplers is independent of the discretization of the function. Second, by exploiting local Hessian information and any associated low-dimensional structure in the change from prior to posterior distributions, we develop an inhomogeneous discretization scheme for the Langevin stochastic differential equation that yields operator-weighted proposals adapted to the non-Gaussian structure of the posterior. The resulting dimension-independent, likelihood-informed (DILI) MCMC samplers may be useful for a large class of high-dimensional problems where the target probability measure has a density with respect to a Gaussian reference measure. Two nonlinear inverse problems are used to demonstrate the efficiency of these DILI samplers: an elliptic PDE coefficient inverse problem and path reconstruction in a conditioned diffusion.
Full work available at URL: https://arxiv.org/abs/1411.3688
Recommendations
- Ensemble sampler for infinite-dimensional inverse problems
- Proposals which speed up function-space MCMC
- Localization for MCMC: sampling high-dimensional posterior distributions with local structure
- Dimension-Independent MCMC Sampling for Inverse Problems with Non-Gaussian Priors
- Adaptive dimension reduction to accelerate infinite-dimensional geometric Markov chain Monte Carlo
Markov chain Monte Carloinfinite-dimensional inverse problemsconditioned diffusionLangevin SDElikelihood-informed subspace
Bayesian inference (62F15) Monte Carlo methods (65C05) Computational methods for stochastic equations (aspects of stochastic analysis) (60H35)
Cites Work
- Sequential Monte Carlo Samplers
- Weak convergence and optimal scaling of random walk Metropolis algorithms
- An adaptive Metropolis algorithm
- Particle Markov Chain Monte Carlo Methods
- Monte Carlo sampling methods using Markov chains and their applications
- Stochastic Equations in Infinite Dimensions
- Finding structure with randomness: probabilistic algorithms for constructing approximate matrix decompositions
- A sequential particle filter method for static models
- A note on Metropolis-Hastings kernels for general state spaces
- Langevin diffusions and Metropolis-Hastings algorithms
- Optimal scaling for various Metropolis-Hastings algorithms.
- Exact and Computationally Efficient Likelihood-Based Estimation for Discretely Observed Diffusion Processes (with Discussion)
- Optimal Scaling of Discrete Approximations to Langevin Diffusions
- Equation of state calculations by fast computing machines
- Coupling and Ergodicity of Adaptive Markov Chain Monte Carlo Algorithms
- On the ergodicity of the adaptive Metropolis algorithm on unbounded domains
- On the ergodicity properties of some adaptive MCMC algorithms
- Riemann manifold Langevin and Hamiltonian Monte Carlo methods. With discussion and authors' reply
- Title not available (Why is that?)
- Inverse problems: a Bayesian perspective
- Multilevel Monte Carlo Path Simulation
- Inverse Problem Theory and Methods for Model Parameter Estimation
- An adaptive version for the Metropolis adjusted Langevin algorithm with a truncated drift
- A stochastic Newton MCMC method for large-scale statistical inverse problems with application to seismic inversion
- Spectral gaps for a Metropolis-Hastings algorithm in infinite dimensions
- MCMC methods for functions: modifying old algorithms to make them faster
- Proposals which speed up function-space MCMC
- A computational framework for infinite-dimensional Bayesian inverse problems. I: The linearized case, with application to global seismic inversion
- Randomized algorithms for the low-rank approximation of matrices
- MCMC METHODS FOR DIFFUSION BRIDGES
- MAP estimators and their consistency in Bayesian nonparametric inverse problems
- Fast algorithms for Bayesian uncertainty quantification in large-scale linear inverse problems based on low-rank partial Hessian approximations
- Title not available (Why is that?)
- Signal processing problems on function space: Bayesian formulation, stochastic PDEs and effective MCMC methods
- Diffusion limits of the random walk Metropolis algorithm in high dimensions
- Optimal scaling and diffusion limits for the Langevin algorithm in high dimensions
- A computational framework for infinite-dimensional Bayesian inverse problems. II: stochastic Newton MCMC with application to ice sheet flow inverse problems
- Complexity analysis of accelerated MCMC methods for Bayesian inversion
- Active subspace methods in theory and practice: applications to kriging surfaces
- Likelihood-informed dimension reduction for nonlinear inverse problems
- A Hierarchical Multilevel Markov Chain Monte Carlo Algorithm with Applications to Uncertainty Quantification in Subsurface Flow
- A stable manifold MCMC method for high dimensions
Cited In (only showing first 100 items - show all)
- Pass-efficient randomized algorithms for low-rank matrix approximation using any number of views
- Solving Bayesian inverse problems from the perspective of deep generative networks
- A Bayesian level set method for an inverse medium scattering problem in acoustics
- Approximation and sampling of multivariate probability distributions in the tensor train decomposition
- Randomized maximum likelihood based posterior sampling
- Wavelet-based priors accelerate maximum-a-posteriori optimization in Bayesian inverse problems
- Likelihood-free inference in high dimensions with synthetic likelihood
- A Randomized Maximum A Posteriori Method for Posterior Sampling of High Dimensional Nonlinear Bayesian Inverse Problems
- A Bayesian method for an inverse transmission scattering problem in acoustics
- Bayesian inference with optimal maps
- Low-rank independence samplers in hierarchical Bayesian inverse problems
- Striated Metropolis-Hastings sampler for high-dimensional models
- On a generalization of the preconditioned Crank-Nicolson metropolis algorithm
- A multiscale strategy for Bayesian inference using transport maps
- Forward and backward uncertainty quantification with active subspaces: application to hypersonic flows around a cylinder
- Certified dimension reduction in nonlinear Bayesian inverse problems
- Iterative importance sampling algorithms for parameter estimation
- Stein variational gradient descent on infinite-dimensional space and applications to statistical inverse problems
- Efficient estimation of hydraulic conductivity heterogeneity with non-redundant measurement information
- Sequential ensemble transform for Bayesian inverse problems
- Image inversion and uncertainty quantification for constitutive laws of pattern formation
- Iterative construction of Gaussian process surrogate models for Bayesian inference
- Bayesian inference of heterogeneous epidemic models: application to COVID-19 spread accounting for long-term care facilities
- Finite element representations of Gaussian processes: balancing numerical and statistical accuracy
- Hessian-based adaptive sparse quadrature for infinite-dimensional Bayesian inverse problems
- Data-free likelihood-informed dimension reduction of Bayesian inverse problems
- Learning physics-based models from data: perspectives from inverse problems and model reduction
- A stable manifold MCMC method for high dimensions
- Accelerated dimension-independent adaptive metropolis
- Data-driven forward discretizations for Bayesian inversion
- Bayesian inversion of a diffusion model with application to biology
- Spatial localization for nonlinear dynamical stochastic models for excitable media
- Scaling limits in computational Bayesian inversion
- Localization for MCMC: sampling high-dimensional posterior distributions with local structure
- Goal-oriented optimal approximations of Bayesian linear inverse problems
- FEM-based discretization-invariant MCMC methods for PDE-constrained Bayesian inverse problems
- A Bayesian level set method for the shape reconstruction of inverse scattering problems in elasticity
- Signal processing problems on function space: Bayesian formulation, stochastic PDEs and effective MCMC methods
- MALA-within-Gibbs samplers for high-dimensional distributions with sparse conditional structure
- Probabilistic parameter estimation in a 2-step chemical kinetics model for n-dodecane jet autoignition
- Optimal low-rank approximations of Bayesian linear inverse problems
- Non-stationary multi-layered Gaussian priors for Bayesian inversion
- A hybrid adaptive MCMC algorithm in function spaces
- Multilevel sequential Monte Carlo with dimension-independent likelihood-informed proposals
- Tensor train construction from tensor actions, with application to compression of large high order derivative tensors
- Affine invariant interacting Langevin dynamics for Bayesian inference
- Multilevel Markov Chain Monte Carlo
- Rate-optimal refinement strategies for local approximation MCMC
- Ensemble sampler for infinite-dimensional inverse problems
- Generalized parallel tempering on Bayesian inverse problems
- A vine-copula based adaptive MCMC sampler for efficient inference of dynamical systems
- Geometric MCMC for infinite-dimensional inverse problems
- Optimization based methods for partially observed chaotic systems
- Scalable posterior approximations for large-scale Bayesian inverse problems via likelihood-informed parameter and state reduction
- Proposals which speed up function-space MCMC
- A computational framework for infinite-dimensional Bayesian inverse problems. II: stochastic Newton MCMC with application to ice sheet flow inverse problems
- An Adaptive Independence Sampler MCMC Algorithm for Bayesian Inferences of Functions
- Efficient parameter estimation for a methane hydrate model with active subspaces
- Bayesian inverse problems with \(l_1\) priors: a randomize-then-optimize approach
- Particle Filtering for Stochastic Navier--Stokes Signal Observed with Linear Additive Noise
- Adaptive dimension reduction to accelerate infinite-dimensional geometric Markov chain Monte Carlo
- Hierarchical Matrix Approximations of Hessians Arising in Inverse Problems Governed by PDEs
- Optimization-Based Markov Chain Monte Carlo Methods for Nonlinear Hierarchical Statistical Inverse Problems
- Efficient Marginalization-Based MCMC Methods for Hierarchical Bayesian Inverse Problems
- Scalable Optimization-Based Sampling on Function Space
- MCMC methods for sampling function space
- Bayesian inference of random fields represented with the Karhunen-Loève expansion
- Survey of multifidelity methods in uncertainty propagation, inference, and optimization
- Multimodal, high-dimensional, model-based, Bayesian inverse problems with applications in biomechanics
- Accelerating Markov chain Monte Carlo with active subspaces
- On an adaptive preconditioned Crank-Nicolson MCMC algorithm for infinite dimensional Bayesian inference
- Scaling Up Bayesian Uncertainty Quantification for Inverse Problems Using Deep Neural Networks
- A posteriori stochastic correction of reduced models in delayed-acceptance MCMC, with application to multiphase subsurface inverse problems
- Variational Bayes' Method for Functions with Applications to Some Inverse Problems
- Adaptive inference over Besov spaces in the white noise model using \(p\)-exponential priors
- Optimal experimental design for infinite-dimensional Bayesian inverse problems governed by PDEs: a review
- Multilevel Hierarchical Decomposition of Finite Element White Noise with Application to Multilevel Markov Chain Monte Carlo
- Residual-based error correction for neural operator accelerated Infinite-dimensional Bayesian inverse problems
- Solution of physics-based inverse problems using conditional generative adversarial networks with full gradient penalty
- Solving linear Bayesian inverse problems using a fractional total variation-Gaussian (FTG) prior and transport map
- A Bayesian approach for consistent reconstruction of inclusions
- Online MCMC Thinning with Kernelized Stein Discrepancy
- Projected Wasserstein Gradient Descent for High-Dimensional Bayesian Inference
- Conditional sampling with monotone GANs: from generative models to likelihood-free inference
- Principal feature detection via \(\phi \)-Sobolev inequalities
- On unifying randomized methods for inverse problems
- Optimal experimental design: formulations and computations
- Two Metropolis--Hastings Algorithms for Posterior Measures with Non-Gaussian Priors in Infinite Dimensions
- Properties of the affine‐invariant ensemble sampler's ‘stretch move’ in high dimensions
- On posterior consistency of data assimilation with Gaussian process priors: the 2D-Navier-Stokes equations
- Multilevel hierarchical decomposition of finite element white noise with application to multilevel Markov chain Monte Carlo
- Multilevel dimension-independent likelihood-informed MCMC for large-scale inverse problems
- Optimal neural network approximation of Wasserstein gradient direction via convex optimization
- Derivative-informed neural operator: an efficient framework for high-dimensional parametric derivative learning
- Analysis of a Class of Multilevel Markov Chain Monte Carlo Algorithms Based on Independent Metropolis–Hastings
- Prior normalization for certified likelihood-informed subspace detection of Bayesian inverse problems
- Sparse approximation of triangular transports. I: The finite-dimensional case
- A unified performance analysis of likelihood-informed subspace methods
- Langevin diffusion for population based sampling with an application in Bayesian inference for pharmacodynamics
- Large-scale Bayesian optimal experimental design with derivative-informed projected neural network
This page was built for publication: Dimension-independent likelihood-informed MCMC
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2374891)
