Adaptive Importance Sampling in General Mixture Classes

Abstract

In this paper, we propose an adaptive algorithm that iteratively updates both the weights and component parameters of a mixture importance sampling density so as to optimise the importance sampling performances, as measured by an entropy criterion. The method is shown to be applicable to a wide class of importance sampling densities, which includes in particular mixtures of multivariate Student t distributions. The performances of the proposed scheme are studied on both artificial and real examples, highlighting in particular the benefit of a novel Rao-Blackwellisation device which can be easily incorporated in the updating scheme.

Removed misleading comment in Section 2

References in corpus (1)

• Convergence of adaptive mixtures of importance sampling schemes

Cited by in corpus (42)

• Adaptive approximate Bayesian computation
• Evidence for the accelerated expansion of the Universe from weak lensing tomography with COSMOS
• CFHTLenS: Combined probe cosmological model comparison using 2D weak gravitational lensing
• Markov Chain Monte Carlo Methods for Bayesian Data Analysis in Astronomy
• Effective Sample Size for Importance Sampling based on discrepancy measures
• A Survey of Monte Carlo Methods for Parameter Estimation
• Galaxy clustering in the CFHTLS-Wide: the changing relationship between galaxies and haloes since z ~ 1.2
• Generalized Multiple Importance Sampling
• Population dynamics method with a multi-canonical feedback control
• Layered Adaptive Importance Sampling
• Improving Population Monte Carlo: Alternative Weighting and Resampling Schemes
• Efficient Multiple Importance Sampling Estimators
• Targeted free energy estimation via learned mappings
• Rethinking the Effective Sample Size
• Bayesian Fit of Exclusive $b\to s\bar{\ell }\ell$ Decays: The Standard Model Operator Basis
• Implicit particle methods and their connection with variational data assimilation
• Importance Gaussian Quadrature
• A population Monte Carlo scheme with transformed weights and its application to stochastic kinetic models
• STROOPWAFEL: Simulating rare outcomes from astrophysical populations, with application to gravitational-wave sources
• Compressed Monte Carlo with application in particle filtering
• TEASING: a fast and accurate approximation for the low multipole likelihood of the Cosmic Microwave Background temperature
• Implicitly Adaptive Importance Sampling
• Forecasts of non-Gaussian parameter spaces using Box-Cox transformations
• Multiplex decomposition of non-Markovian dynamics and the hidden layer reconstruction problem
• Particle Smoothing for Hidden Diffusion Processes: Adaptive Path Integral Smoother
• Robust Covariance Adaptation in Adaptive Importance Sampling
• (MC)**3 -- a Multi-Channel Markov Chain Monte Carlo algorithm for phase-space sampling
• Bayesian Model Averaging in Astrophysics: A Review
• Bayesian model comparison in cosmology with Population Monte Carlo
• Optimized Population Monte Carlo
• Approximating Probability Densities by Iterated Laplace Approximations
• Hamiltonian Adaptive Importance Sampling
• A nonlinear population Monte Carlo scheme for the Bayesian estimation of parameters of $\alpha$-stable distributions
• Rare Events via Cross-Entropy Population Monte Carlo
• The Megopolis Resampler: Memory Coalesced Resampling on GPUs
• Population Quasi-Monte Carlo
• Composite likelihood inference for the Poisson log-normal model
• Deep Importance Sampling based on Regression for Model Inversion and Emulation
• Advances in Importance Sampling
• Effective sample size approximations as entropy measures
• Importance sampling-based gradient method for dimension reduction in Poisson log-normal model
• Simulating signed mixtures