Layered adaptive importance sampling
From MaRDI portal
Publication:2361441
Abstract: Monte Carlo methods represent the "de facto" standard for approximating complicated integrals involving multidimensional target distributions. In order to generate random realizations from the target distribution, Monte Carlo techniques use simpler proposal probability densities to draw candidate samples. The performance of any such method is strictly related to the specification of the proposal distribution, such that unfortunate choices easily wreak havoc on the resulting estimators. In this work, we introduce a layered (i.e., hierarchical) procedure to generate samples employed within a Monte Carlo scheme. This approach ensures that an appropriate equivalent proposal density is always obtained automatically (thus eliminating the risk of a catastrophic performance), although at the expense of a moderate increase in the complexity. Furthermore, we provide a general unified importance sampling (IS) framework, where multiple proposal densities are employed and several IS schemes are introduced by applying the so-called deterministic mixture approach. Finally, given these schemes, we also propose a novel class of adaptive importance samplers using a population of proposals, where the adaptation is driven by independent parallel or interacting Markov Chain Monte Carlo (MCMC) chains. The resulting algorithms efficiently combine the benefits of both IS and MCMC methods.
Recommendations
Cites work
- A generalization of the adaptive rejection sampling algorithm
- A sequential particle filter method for static models
- Adaptive multiple importance sampling
- Advanced Markov chain Monte Carlo methods. Learning from past samples.
- An adaptive Metropolis algorithm
- An Adaptive Population Importance Sampler: Learning From Uncertainty
- An adaptive sequential Monte Carlo sampler
- An efficient algorithm for rare-event probability estimation, combinatorial optimization, and counting
- An introduction to MCMC for machine learning
- Computing the Bayes factor from a Markov chain Monte Carlo simulation of the posterior distribution
- Consistency of adaptive importance sampling and recycling schemes
- Convergence of adaptive mixtures of importance sampling schemes
- Generalized multiple importance sampling
- scientific article; zbMATH DE number 5919872 (Why is no real title available?)
- scientific article; zbMATH DE number 2117879 (Why is no real title available?)
- Improving MCMC, using efficient importance sampling
- Learn from thy neighbor: parallel-chain and regional adaptive MCMC
- Marginal Likelihood From the Metropolis–Hastings Output
- Markov chain importance sampling with applications to rare event probability estimation
- Markov chain Monte Carlo methods with applications to signal processing.
- MCMC-driven adaptive multiple importance sampling
- Minimum variance importance samplingviaPopulation Monte Carlo
- Monte Carlo Bayesian signal processing for wireless communications
- Nested sampling for general Bayesian computation
- Particle Markov chain Monte Carlo for efficient numerical simulation
- Safe and Effective Importance Sampling
- Sequential Monte Carlo on large binary sampling spaces
- Sequential Monte Carlo Samplers
- Sequentially interacting Markov chain Monte Carlo methods
- The Multiple-Try Method and Local Optimization in Metropolis Sampling
Cited in
(36)- Efficient importance sampling in low dimensions using affine arithmetic
- Langevin incremental mixture importance sampling
- Implicitly adaptive importance sampling
- Integrating geostatistical maps and infectious disease transmission models using adaptive multiple importance sampling
- Proximal nested sampling for high-dimensional Bayesian model selection
- A principled stopping rule for importance sampling
- MCMC-driven importance samplers
- Compressed Monte Carlo with application in particle filtering
- On a Metropolis-Hastings importance sampling estimator
- Generalized multiple importance sampling
- Issues in the multiple try Metropolis mixing
- Consistency of adaptive importance sampling and recycling schemes
- Moment matching adaptive importance sampling with skew-Student proposals
- Layer sampling
- scientific article; zbMATH DE number 1054684 (Why is no real title available?)
- Target-aware Bayesian inference: how to beat optimal conventional estimators
- Markov Chain Importance Sampling—A Highly Efficient Estimator for MCMC
- Transport map accelerated adaptive importance sampling, and application to inverse problems arising from multiscale stochastic reaction networks
- Adaptive importance sampling Monte Carlo simulation for general multivariate probability laws
- Ensemble transport adaptive importance sampling
- MCMC-driven adaptive multiple importance sampling
- Marginal Likelihood Computation for Model Selection and Hypothesis Testing: An Extensive Review
- Warp Bridge Sampling: The Next Generation
- Daisee: Adaptive importance sampling by balancing exploration and exploitation
- Rethinking the Effective Sample Size
- Gradient-based adaptive importance samplers
- Efficient Bayes inference in neural networks through adaptive importance sampling
- Inference over radiative transfer models using variational and expectation maximization methods
- Wavelet Monte Carlo: a principle for sampling from complex distributions
- Variance analysis of multiple importance sampling schemes
- A novel method for damage identification based on tuning-free strategy and simple population Metropolis-Hastings algorithm
- Transporting higher-order quadrature rules -- quasi-Monte Carlo points and sparse grids for mixture distributions
- Global convergence of optimized adaptive importance samplers
- Annealing strategies for variance reduction in balance heuristic estimators
- Adaptive posterior distributions for uncertainty analysis of covariance matrices in Bayesian inversion problems for multioutput signals
- Enhanced convergence rates of adaptive importance sampling with recycling schemes via quasi-Monte Carlo methods
This page was built for publication: Layered adaptive importance sampling
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2361441)
