Target-aware Bayesian inference: how to beat optimal conventional estimators

zbMATH Open1504.62036MaRDI QIDQ4969150FDOQ4969150

Authors: Tom Rainforth, Adam Goliński, Frank Wood, Sheheryar Zaidi 

Publication date: 5 October 2020

Full work available at URL: https://jmlr.csail.mit.edu/papers/v21/19-102.html

Recommendations

• Transport map accelerated Markov chain Monte Carlo
• Bayesian inference with optimal maps
• Elements of sequential Monte Carlo
• Informed sub-sampling MCMC: approximate Bayesian inference for large datasets
• Targeting Bayes factors with direct-path non-equilibrium thermodynamic integration

zbMATH Keywords

Bayesian inferenceimportance samplingMonte Carlo methodsadaptive samplingamortized inference

Mathematics Subject Classification ID

Bayesian inference (62F15) Monte Carlo methods (65C05)

Cites Work

• The sample size required in importance sampling
• Sequential Monte Carlo Methods in Practice
• The Bayesian Choice
• Estimating marginal likelihoods for mixture and Markov switching models using bridge sampling techniques*
• Methods for approximating integrals in statistics with special emphasis on Bayesian integration problems
• Title not available (Why is that?)
• Title not available (Why is that?)
• Simulating normalizing constants: From importance sampling to bridge sampling to path sampling
• On Monte Carlo methods for estimating ratios of normalizing constants
• Properties of nested sampling
• Adaptive multiple importance sampling
• Safe and Effective Importance Sampling
• Some summation formulas involving harmonic numbers and generalized harmonic numbers
• Methods of reducing sample size in Monte Carlo computations
• Convergence of adaptive mixtures of importance sampling schemes
• Adaptive umbrella sampling: Self-consistent determination of the non- Boltzmann bias
• Title not available (Why is that?)
• Adaptive importance sampling in monte carlo integration
• A tutorial on bridge sampling
• Layered adaptive importance sampling
• Generalized multiple importance sampling
• Title not available (Why is that?)

Cited In (2)

• Daisee: Adaptive importance sampling by balancing exploration and exploitation
• Target-aware Bayesian inference via generalized thermodynamic integration

This page was built for publication: Target-aware Bayesian inference: how to beat optimal conventional estimators

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4969150)