Iterative importance sampling algorithms for parameter estimation
From MaRDI portal
Publication:4607633
DOI10.1137/16M1088417zbMATH Open1385.65007arXiv1608.01958OpenAlexW2769566789WikidataQ130175704 ScholiaQ130175704MaRDI QIDQ4607633FDOQ4607633
Authors: Matthias Morzfeld, M. S. Day, R. W. Grout, George Shu Heng Pau, Stefan Finsterle, J. B. Bell 
Publication date: 14 March 2018
Published in: SIAM Journal on Scientific Computing (Search for Journal in Brave)
Abstract: In parameter estimation problems one computes a posterior distribution over uncertain parameters defined jointly by a prior distribution, a model, and noisy data. Markov Chain Monte Carlo (MCMC) is often used for the numerical solution of such problems. An alternative to MCMC is importance sampling, which can exhibit near perfect scaling with the number of cores on high performance computing systems because samples are drawn independently. However, finding a suitable proposal distribution is a challenging task. Several sampling algorithms have been proposed over the past years that take an iterative approach to constructing a proposal distribution. We investigate the applicability of such algorithms by applying them to two realistic and challenging test problems, one in subsurface flow, and one in combustion modeling. More specifically, we implement importance sampling algorithms that iterate over the mean and covariance matrix of Gaussian or multivariate t-proposal distributions. Our implementation leverages massively parallel computers, and we present strategies to initialize the iterations using "coarse" MCMC runs or Gaussian mixture models.
Full work available at URL: https://arxiv.org/abs/1608.01958
Recommendations
Cites Work
- MCMC using Hamiltonian dynamics
- Sequential Monte Carlo Methods in Practice
- Sequential Monte Carlo Samplers
- An adaptive Metropolis algorithm
- Nonlinear data assimilation
- Curse-of-dimensionality revisited: Collapse of the particle filter in very large scale systems
- A random map implementation of implicit filters
- Can local particle filters beat the curse of dimensionality?
- Sequential Monte Carlo Methods for Dynamic Systems
- An Algorithm for Least-Squares Estimation of Nonlinear Parameters
- Optimal Scaling of Discrete Approximations to Langevin Diffusions
- A method for the solution of certain non-linear problems in least squares
- Ensemble samplers with affine invariance
- Riemann manifold Langevin and Hamiltonian Monte Carlo methods. With discussion and authors' reply
- Inverse problems: a Bayesian perspective
- Parameter and state model reduction for large-scale statistical inverse problems
- Sampling, feasibility, and priors in data assimilation
- Small-noise analysis and symmetrization of implicit Monte Carlo samplers
- CAPILLARY CONDUCTION OF LIQUIDS THROUGH POROUS MEDIUMS
- Title not available (Why is that?)
- Stochastic tools in mathematics and science
- Implicit particle filters for data assimilation
- Bayesian inference with optimal maps
- Parameter estimation by implicit sampling
- VODE: A Variable-Coefficient ODE Solver
- Nonparametric Importance Sampling
- Inverse Problem Theory and Methods for Model Parameter Estimation
- A stochastic Newton MCMC method for large-scale statistical inverse problems with application to seismic inversion
- MCMC methods for functions: modifying old algorithms to make them faster
- A computational framework for infinite-dimensional Bayesian inverse problems. I: The linearized case, with application to global seismic inversion
- Title not available (Why is that?)
- Sequential Monte Carlo methods for Bayesian elliptic inverse problems
- Population Monte Carlo algorithm in high dimensions
- Fast algorithms for Bayesian uncertainty quantification in large-scale linear inverse problems based on low-rank partial Hessian approximations
- Minimization for conditional simulation: relationship to optimal transport
- Pushing the Limits of Contemporary Statistics: Contributions in Honor of Jayanta K. Ghosh
- Convergence of adaptive mixtures of importance sampling schemes
- Local Adaptive Importance Sampling for Multivariate Densities With Strong Nonlinear Relationships
- A computational framework for infinite-dimensional Bayesian inverse problems. II: stochastic Newton MCMC with application to ice sheet flow inverse problems
- Limitations of polynomial chaos expansions in the Bayesian solution of inverse problems
- Likelihood-informed dimension reduction for nonlinear inverse problems
- Adaptive importance sampling in monte carlo integration
- Dimension-independent likelihood-informed MCMC
- Iterative Bayesian inversion with Gaussian mixtures: finite sample implementation and large sample asymptotics
- Scalable posterior approximations for large-scale Bayesian inverse problems via likelihood-informed parameter and state reduction
- Optimal low-rank approximations of Bayesian linear inverse problems
- Adaptive independent Metropolis-Hastings
- Randomize-then-optimize: a method for sampling from posterior distributions in nonlinear inverse problems
- Implicit sampling, with application to data assimilation
- Transport map accelerated Markov chain Monte Carlo
- A multiscale strategy for Bayesian inference using transport maps
Cited In (13)
- Bayesian updating and marginal likelihood estimation by cross entropy based importance sampling
- A Sample-Wise Data Driven Control Solver for the Stochastic Optimal Control Problem with Unknown Model Parameters
- Iterative construction of Gaussian process surrogate models for Bayesian inference
- A direct filter method for parameter estimation
- Iterated importance sampling in missing data problems
- Efficient simulated maximum likelihood estimation through explicitly parameter dependent importance sampling
- Iterative importance sampling with Markov chain Monte Carlo sampling in robust Bayesian analysis
- A backward SDE method for uncertainty quantification in deep learning
- An adaptive importance sampling algorithm for Bayesian inversion with multimodal distributions
- A Continuation Method in Bayesian Inference
- A fast particle-based approach for calibrating a 3-D model of the Antarctic ice sheet
- On spatially correlated observations in importance sampling methods for subsidence estimation
- A bi-fidelity ensemble Kalman method for PDE-constrained inverse problems in computational mechanics
Uses Software
This page was built for publication: Iterative importance sampling algorithms for parameter estimation
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4607633)
