Scalable Optimization-Based Sampling on Function Space
From MaRDI portal
Abstract: Optimization-based samplers such as randomize-then-optimize (RTO) [2] provide an efficient and parallellizable approach to solving large-scale Bayesian inverse problems. These methods solve randomly perturbed optimization problems to draw samples from an approximate posterior distribution. "Correcting" these samples, either by Metropolization or importance sampling, enables characterization of the original posterior distribution. This paper focuses on the scalability of RTO to problems with high- or infinite-dimensional parameters. We introduce a new subspace acceleration strategy that makes the computational complexity of RTO scale linearly with the parameter dimension. This subspace perspective suggests a natural extension of RTO to a function space setting. We thus formalize a function space version of RTO and establish sufficient conditions for it to produce a valid Metropolis-Hastings proposal, yielding dimension-independent sampling performance. Numerical examples corroborate the dimension-independence of RTO and demonstrate sampling performance that is also robust to small observational noise.
Recommendations
- Randomize-then-optimize: a method for sampling from posterior distributions in nonlinear inverse problems
- An Acceleration Strategy for Randomize-Then-Optimize Sampling Via Deep Neural Networks
- A Metropolis-Hastings-within-Gibbs sampler for nonlinear hierarchical-Bayesian inverse problems
- Randomize-then-optimize for sampling and uncertainty quantification in electrical impedance tomography
- Scalable posterior approximations for large-scale Bayesian inverse problems via likelihood-informed parameter and state reduction
Cites work
- scientific article; zbMATH DE number 2000348 (Why is no real title available?)
- scientific article; zbMATH DE number 6159604 (Why is no real title available?)
- scientific article; zbMATH DE number 5060482 (Why is no real title available?)
- A Hierarchical Multilevel Markov Chain Monte Carlo Algorithm with Applications to Uncertainty Quantification in Subsurface Flow
- 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 computational framework for infinite-dimensional Bayesian inverse problems. II: stochastic Newton MCMC with application to ice sheet flow inverse problems
- A note on Metropolis-Hastings kernels for general state spaces
- A random map implementation of implicit filters
- A stochastic Newton MCMC method for large-scale statistical inverse problems with application to seismic inversion
- An Interior Trust Region Approach for Nonlinear Minimization Subject to Bounds
- An explicit link between Gaussian fields and Gaussian Markov random fields: the stochastic partial differential equation approach
- An introduction to infinite-dimensional analysis
- Bayesian inverse problems with l₁ priors: a randomize-then-optimize approach
- Certified dimension reduction in nonlinear Bayesian inverse problems
- Complexity analysis of accelerated MCMC methods for Bayesian inversion
- Diffusion limits of the random walk Metropolis algorithm in high dimensions
- Dimension-independent likelihood-informed MCMC
- Exponential convergence of Langevin distributions and their discrete approximations
- Fast algorithms for Bayesian uncertainty quantification in large-scale linear inverse problems based on low-rank partial Hessian approximations
- Finding structure with randomness: probabilistic algorithms for constructing approximate matrix decompositions
- Geometric MCMC for infinite-dimensional inverse problems
- Handbook of Markov Chain Monte Carlo
- Implicit particle filters for data assimilation
- Importance sampling: intrinsic dimension and computational cost
- Inverse problems: a Bayesian perspective
- Likelihood-informed dimension reduction for nonlinear inverse problems
- MCMC METHODS FOR DIFFUSION BRIDGES
- MCMC methods for functions: modifying old algorithms to make them faster
- Metropolized randomized maximum likelihood for improved sampling from multimodal distributions
- Multilevel Monte Carlo Path Simulation
- On a generalization of the preconditioned Crank-Nicolson metropolis algorithm
- On the convergence of interior-reflective Newton methods for nonlinear minimization subject to bounds
- Optimal low-rank approximations of Bayesian linear inverse problems
- Optimal model management for multifidelity Monte Carlo estimation
- Parallel local approximation MCMC for expensive models
- Randomize-then-optimize: a method for sampling from posterior distributions in nonlinear inverse problems
- Rates of convergence of the Hastings and Metropolis algorithms
- Riemann manifold Langevin and Hamiltonian Monte Carlo methods. With discussion and authors' reply
- Scalable posterior approximations for large-scale Bayesian inverse problems via likelihood-informed parameter and state reduction
- Statistical and computational inverse problems.
- Transport map accelerated Markov chain Monte Carlo
- Weak convergence and optimal scaling of random walk Metropolis algorithms
Cited in
(13)- Randomized maximum likelihood based posterior sampling
- Uncertainty quantification for linear inverse problems with Besov prior: a randomize-then-optimize method
- Optimal experimental design for infinite-dimensional Bayesian inverse problems governed by PDEs: a review
- A Metropolis-Hastings-within-Gibbs sampler for nonlinear hierarchical-Bayesian inverse problems
- PyOED: an extensible suite for data assimilation and model-constrained optimal design of experiments
- Learning physics-based models from data: perspectives from inverse problems and model reduction
- Numerical algorithms for spline interpolation on space of probability density functions
- MALA-within-Gibbs samplers for high-dimensional distributions with sparse conditional structure
- Randomize-then-optimize: a method for sampling from posterior distributions in nonlinear inverse problems
- Efficient evaluation of oversampled functions
- Variational inference for nonlinear inverse problems via neural net kernels: comparison to Bayesian neural networks, application to topology optimization
- Optimization-Based Markov Chain Monte Carlo Methods for Nonlinear Hierarchical Statistical Inverse Problems
- hIPPYlib-MUQ: a Bayesian inference software framework for integration of data with complex predictive models under uncertainty
This page was built for publication: Scalable Optimization-Based Sampling on Function Space
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5112552)
