Importance sampling: intrinsic dimension and computational cost

DOI10.1214/17-STS611zbMath1442.62026arXiv1511.06196MaRDI QIDQ1750255

Andrew M. Stuart, Daniel Sanz-Alonso, Sergios Agapiou, Omiros Papaspiliopoulos

Publication date: 18 May 2018

Published in: Statistical Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1511.06196

zbMATH Keywords

importance samplinginverse problemsfilteringabsolute continuitycomputational costsmall noisenotions of dimension

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Sampling theory, sample surveys (62D05)

Related Items (53)

A Variational Inference Approach to Inverse Problems with Gamma Hyperpriors ⋮ An Invitation to Sequential Monte Carlo Samplers ⋮ Importance Sampling and Necessary Sample Size: An Information Theory Approach ⋮ Continuum Limits of Posteriors in Graph Bayesian Inverse Problems ⋮ Reduced modeling of unknown trajectories ⋮ Unnamed Item ⋮ The sample size required in importance sampling ⋮ Unnamed Item ⋮ Certified dimension reduction in nonlinear Bayesian inverse problems ⋮ Autodifferentiable Ensemble Kalman Filters ⋮ On a Metropolis-Hastings importance sampling estimator ⋮ Moment matching adaptive importance sampling with skew-Student proposals ⋮ Iterative importance sampling with Markov chain Monte Carlo sampling in robust Bayesian analysis ⋮ Overcoming the timescale barrier in molecular dynamics: Transfer operators, variational principles and machine learning ⋮ A unified performance analysis of likelihood-informed subspace methods ⋮ Reduced-order autodifferentiable ensemble Kalman filters ⋮ Scaling limits in computational Bayesian inversion ⋮ Rethinking the Effective Sample Size ⋮ Gradient-based adaptive importance samplers ⋮ Properties of marginal sequential Monte Carlo methods ⋮ Context-Aware Surrogate Modeling for Balancing Approximation and Sampling Costs in Multifidelity Importance Sampling and Bayesian Inverse Problems ⋮ Ensemble MCMC: accelerating pseudo-marginal MCMC for state space models using the ensemble Kalman filter ⋮ A fast particle-based approach for calibrating a 3-D model of the Antarctic ice sheet ⋮ Analysis of a Computational Framework for Bayesian Inverse Problems: Ensemble Kalman Updates and MAP Estimators under Mesh Refinement ⋮ Distilling Importance Sampling for Likelihood Free Inference ⋮ Efficient importance sampling in low dimensions using affine arithmetic ⋮ A Continuation Method in Bayesian Inference ⋮ Scalable Optimization-Based Sampling on Function Space ⋮ A PRticle filter algorithm for nonparametric estimation of multivariate mixing distributions ⋮ Variance analysis of multiple importance sampling schemes ⋮ Adaptive tuning of Hamiltonian Monte Carlo within sequential Monte Carlo ⋮ Iterative updating of model error for Bayesian inversion ⋮ Localization for MCMC: sampling high-dimensional posterior distributions with local structure ⋮ Kernel Methods for Bayesian Elliptic Inverse Problems on Manifolds ⋮ A Practical Example for the Non-linear Bayesian Filtering of Model Parameters ⋮ MALA-within-Gibbs Samplers for High-Dimensional Distributions with Sparse Conditional Structure ⋮ Multilevel Sequential Importance Sampling for Rare Event Estimation ⋮ Importance sampling: intrinsic dimension and computational cost ⋮ Multilevel ensemble Kalman filtering for spatio-temporal processes ⋮ Convergence rates for optimised adaptive importance samplers ⋮ Pricing discretely-monitored double barrier options with small probabilities of execution ⋮ Multilevel sequential Monte Carlo for Bayesian inverse problems ⋮ Symmetrized importance samplers for stochastic differential equations ⋮ Rates of contraction of posterior distributions based on \(p\)-exponential priors ⋮ Efficient probabilistic reconciliation of forecasts for real-valued and count time series ⋮ Data-driven forward discretizations for Bayesian inversion ⋮ Improving Approximate Bayesian Computation via Quasi-Monte Carlo ⋮ Bayesian Parameter Identification in Cahn--Hilliard Models for Biological Growth ⋮ Data assimilation: The Schrödinger perspective ⋮ Product-form estimators: exploiting independence to scale up Monte Carlo ⋮ A weighted discrepancy bound of quasi-Monte Carlo importance sampling ⋮ The Ensemble Kalman Filter for Rare Event Estimation ⋮ Quasi-Monte Carlo and Multilevel Monte Carlo Methods for Computing Posterior Expectations in Elliptic Inverse Problems

Uses Software

• PRMLT

Cites Work

• Can local particle filters beat the curse of dimensionality?
• Oracle-type posterior contraction rates in Bayesian inverse problems
• Bayesian inverse problems with non-conjugate priors
• Non-Gaussian statistical inverse problems. Part I: Posterior distributions
• Non-Gaussian statistical inverse problems. II: Posterior convergence for approximated unknowns
• Evaluation for moments of a ratio with application to regression estimation
• Bayesian inverse problems with Gaussian priors
• On the convergence of two sequential Monte Carlo methods for maximum a posteriori sequence estimation and stochastic global optimization
• The expected ratio of the sum of squares to the square of the sum
• Estimation of high-dimensional prior and posterior covariance matrices in Kalman filter vari\-ants
• Parameter estimation by implicit sampling
• Fundamentals of stochastic filtering
• A note on auxiliary particle filters
• The ratio of the extreme to the sum in a random sequence
• A note on Metropolis-Hastings kernels for general state spaces
• The sample size required in importance sampling
• Importance sampling: intrinsic dimension and computational cost
• Statistical and computational inverse problems.
• Sharp adaptation for inverse problems with random noise
• Smoothness and dimension reduction in quasi-Monte Carlo methods
• Large deviations and importance sampling for systems of slow-fast motion
• Bayesian posterior contraction rates for linear severely ill-posed inverse problems
• Optimal rates for the regularized least-squares algorithm
• Central limit theorem for sequential Monte Carlo methods and its application to Bayesian inference
• Discrepancy based model selection in statistical inverse problems
• Posterior contraction rates for the Bayesian approach to linear ill-posed inverse problems
• Monte Carlo strategies in scientific computing.
• Another look at rejection sampling through importance sampling
• On the stability of sequential Monte Carlo methods in high dimensions
• Well-posed stochastic extensions of ill-posed linear problems
• Posterior consistency and convergence rates for Bayesian inversion with hypoelliptic operators
• Small-Noise Analysis and Symmetrization of Implicit Monte Carlo Samplers
• Bridging the ensemble Kalman and particle filters
• Analysis of the Hessian for inverse scattering problems: I. Inverse shape scattering of acoustic waves
• Inverse problems: A Bayesian perspective
• A Stochastic Newton MCMC Method for Large-Scale Statistical Inverse Problems with Application to Seismic Inversion
• Importance Sampling for Multiscale Diffusions
• Likelihood-informed dimension reduction for nonlinear inverse problems
• Active Subspaces
• Importance Sampling and Necessary Sample Size: An Information Theory Approach
• Optimal Low-rank Approximations of Bayesian Linear Inverse Problems
• Pushing the Limits of Contemporary Statistics: Contributions in Honor of Jayanta K. Ghosh
• Curse-of-dimensionality revisited: Collapse of the particle filter in very large scale systems
• Sequential Imputations and Bayesian Missing Data Problems
• Sequential Monte Carlo Methods for Dynamic Systems
• Filtering via Simulation: Auxiliary Particle Filters
• Safe and Effective Importance Sampling
• Linear and Nonlinear Inverse Problems with Practical Applications
• Rare Event Simulation of Small Noise Diffusions
• On a Likelihood Approach for Monte Carlo Integration
• Bayesian Measures of Model Complexity and Fit
• Linear inverse problems for generalised random variables
• Linear estimators and measurable linear transformations on a Hilbert space
• On Choosing and Bounding Probability Metrics
• Bayesian Recovery of the Initial Condition for the Heat Equation
• An Introduction to Sequential Monte Carlo
• A stable particle filter for a class of high-dimensional state-space models
• Stochastic Approximation in Monte Carlo Computation
• A survey of convergence results on particle filtering methods for practitioners
• Methods of Reducing Sample Size in Monte Carlo Computations
• A Computational Framework for Infinite-Dimensional Bayesian Inverse Problems Part I: The Linearized Case, with Application to Global Seismic Inversion
• Two-Stage Importance Sampling With Mixture Proposals
• Posterior consistency for Bayesian inverse problems through stability and regression results
• Learning Bounds for Kernel Regression Using Effective Data Dimensionality
• On the best constant in Marcinkiewicz-Zygmund inequality
• On the role of interaction in sequential Monte Carlo algorithms
• MCMC methods for functions: modifying old algorithms to make them faster
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Importance sampling: intrinsic dimension and computational cost