A Survey of Monte Carlo Methods for Parameter Estimation

Abstract

Statistical signal processing applications usually require the estimation of some parameters of interest given a set of observed data. These estimates are typically obtained either by solving a multi-variate optimization problem, as in the maximum likelihood (ML) or maximum a posteriori (MAP) estimators, or by performing a multi-dimensional integration, as in the minimum mean squared error (MMSE) estimators. Unfortunately, analytical expressions for these estimators cannot be found in most real-world applications, and the Monte Carlo (MC) methodology is one feasible approach. MC methods proceed by drawing random samples, either from the desired distribution or from a simpler one, and using them to compute consistent estimators. The most important families of MC algorithms are Markov chain MC (MCMC) and importance sampling (IS). On the one hand, MCMC methods draw samples from a proposal density, building then an ergodic Markov chain whose stationary distribution is the desired distribution by accepting or rejecting those candidate samples as the new state of the chain. On the other hand, IS techniques draw samples from a simple proposal density, and then assign them suitable weights that measure their quality in some appropriate way. In this paper, we perform a thorough review of MC methods for the estimation of static parameters in signal processing applications. A historical note on the development of MC schemes is also provided, followed by the basic MC method and a brief description of the rejection sampling (RS) algorithm, as well as three sections describing many of the most relevant MCMC and IS algorithms, and their combined use.

References in corpus (37)

• MCMC using Hamiltonian dynamics
• The pseudo-marginal approach for efficient Monte Carlo computations
• Adaptive Importance Sampling in General Mixture Classes
• Effective Sample Size for Importance Sampling based on discrepancy measures
• Cooperative Parallel Particle Filters for online model selection and applications to Urban Mobility
• Irreversible Monte Carlo Algorithms for Efficient Sampling
• Optimal scalings for local Metropolis--Hastings chains on nonproduct targets in high dimensions
• Layered Adaptive Importance Sampling
• Improved Adaptive Rejection Metropolis Sampling Algorithms
• A Review of Multiple Try MCMC algorithms for Signal Processing
• Improving Population Monte Carlo: Alternative Weighting and Resampling Schemes
• Optimal scaling for partially updating MCMC algorithms
• Orthogonal parallel MCMC methods for sampling and optimization
• Optimal scaling and diffusion limits for the Langevin algorithm in high dimensions
• Efficient Multiple Importance Sampling Estimators
• Population Monte Carlo algorithms
• Non-reversible Metropolis-Hastings
• On the role of interaction in sequential Monte Carlo algorithms
• Generalized Rejection Sampling Schemes and Applications in Signal Processing
• A population Monte Carlo scheme with transformed weights and its application to stochastic kinetic models
• On the flexibility of the design of Multiple Try Metropolis schemes
• On the stability and ergodicity of adaptive scaling Metropolis algorithms
• Fully Adaptive Gaussian Mixture Metropolis-Hastings Algorithm
• Interacting Multiple Try Algorithms with Different Proposal Distributions
• Heretical Multiple Importance Sampling
• GPU-accelerated Gibbs sampling: a case study of the Horseshoe Probit model
• A multi-point Metropolis scheme with generic weight functions
• The Recycling Gibbs Sampler for Efficient Learning
• A proof of uniform convergence over time for a distributed particle filter
• Metropolis Sampling
• Combining Particle MCMC with Rao-Blackwellized Monte Carlo Data Association for Parameter Estimation in Multiple Target Tracking
• Adaptive Independent Sticky MCMC algorithms
• Independent Resampling Sequential Monte Carlo Algorithms
• Issues in the Multiple Try Metropolis mixing
• Small-world MCMC and convergence to multi-modal distributions: From slow mixing to fast mixing
• Pólya Urn Latent Dirichlet Allocation: a doubly sparse massively parallel sampler
• Parallel Metropolis chains with cooperative adaptation

Cited by in corpus (18)

• ISFL: Federated Learning for Non-i.i.d. Data with Local Importance Sampling
• Goal-Oriented Scheduling in Sensor Networks with Application Timing Awareness
• Graphical Inference in Linear-Gaussian State-Space Models
• An exhaustive variable selection study for linear models of soundscape emotions: rankings and Gibbs analysis
• CUQIpy: I. Computational uncertainty quantification for inverse problems in Python
• Covid19 Reproduction Number: Credibility Intervals by Blockwise Proximal Monte Carlo Samplers
• Bayesian Safety Validation for Failure Probability Estimation of Black-Box Systems
• A survey of Monte Carlo methods for noisy and costly densities with application to reinforcement learning and ABC
• Hit and Run Sampling from Tropically Convex Sets
• Bayesian Active Search on Parameter Space: a 95 GeV Spin-0 Resonance in the ($B-L$)SSM
• Markov Chain Monte Carlo for generating ranked textual data
• Ensemble Differential Evolution with Simulation-Based Hybridization and Self-Adaptation for Inventory Management Under Uncertainty
• Multi-Physics-Enhanced Bayesian Inverse Analysis: Information Gain from Additional Fields
• Efficient sampling of non log-concave posterior distributions with mixture of noises
• Bayesian Adaptive Trials for Social Policy
• Analysis of sloppiness in model simulations: unveiling parameter uncertainty when mathematical models are fitted to data
• Selecting fitted models under epistemic uncertainty using a stochastic process on quantile functions
• Fourier Series-Based Approximation of Time-Varying Parameters in Ordinary Differential Equations