Layered Adaptive Importance Sampling

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.

Related Matlab codes: an iterative version at http://www.lucamartino.altervista.org/CODE_LAIS_v03.zip and a non-iterative version at http://www.lucamartino.altervista.org/LAIS_non_iterative_code.zip, Statistics and Computing, 2016

References in corpus (7)

• Adaptive Importance Sampling in General Mixture Classes
• Generalized Multiple Importance Sampling
• Efficient Multiple Importance Sampling Estimators
• Sequentially interacting Markov chain Monte Carlo methods
• MCMC Using Ensembles of States for Problems with Fast and Slow Variables such as Gaussian Process Regression
• Target Density Normalization for Markov Chain Monte Carlo Algorithms
• Markov Interacting Importance Samplers

Cited by in corpus (33)

• A Survey of Monte Carlo Methods for Parameter Estimation
• Generalized Multiple Importance Sampling
• A Review of Multiple Try MCMC algorithms for Signal Processing
• Marginal likelihood computation for model selection and hypothesis testing: an extensive review
• Rethinking the Effective Sample Size
• Group Importance Sampling for Particle Filtering and MCMC
• Importance Gaussian Quadrature
• Compressed Monte Carlo with application in particle filtering
• Metropolis Sampling
• Proximal nested sampling for high-dimensional Bayesian model selection
• Optimized Population Monte Carlo
• Issues in the Multiple Try Metropolis mixing
• Adaptive quadrature schemes for Bayesian inference via active learning
• Hamiltonian Adaptive Importance Sampling
• MCMC-driven importance samplers
• Rare Events via Cross-Entropy Population Monte Carlo
• Warp Bridge Sampling: The Next Generation
• On a Metropolis-Hastings importance sampling estimator
• Inference over radiative transfer models using variational and expectation maximization methods
• Divide, Conquer, and Combine: a New Inference Strategy for Probabilistic Programs with Stochastic Support
• A Bayesian inference and model selection algorithm with an optimisation scheme to infer the model noise power
• Inference Trees: Adaptive Inference with Exploration
• Parallel Metropolis chains with cooperative adaptation
• Symbolic Parallel Adaptive Importance Sampling for Probabilistic Program Analysis
• Tree pyramidal adaptive importance sampling
• Consistent Adaptive Multiple Importance Sampling and Controlled Diffusions
• Adaptive posterior distributions for uncertainty analysis of covariance matrices in Bayesian inversion problems for multioutput signals
• Deep Importance Sampling based on Regression for Model Inversion and Emulation
• Revisiting the balance heuristic for estimating normalising constants
• Advances in Importance Sampling
• Automatic tempered posterior distributions for Bayesian inversion problems
• Meta-Learning an Inference Algorithm for Probabilistic Programs
• Estimation and prediction for spatial generalized linear mixed models with parametric links via reparameterized importance sampling