A path sampling identity for computing the Kullback-Leibler and J divergences

DOI10.1016/j.csda.2010.01.018zbMath1284.62097OpenAlexW2092429479MaRDI QIDQ2445627

Geneviève Lefebvre, Alain C. Vandal, Russell J. Steele

Publication date: 14 April 2014

Published in: Computational Statistics and Data Analysis (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.csda.2010.01.018

zbMATH Keywords

model selectionpath samplingKullback-Leibler divergencenormalizing constantgeometric pathauxiliary densityJ divergence

Mathematics Subject Classification ID

Sampling theory, sample surveys (62D05)

Related Items

Thermodynamic Bayesian model comparison ⋮ A Monte Carlo approach to quantifying model error in Bayesian parameter estimation ⋮ A Monte Carlo approach to quantifying discrepancies between intractable posterior distributions ⋮ A Continuation Method in Bayesian Inference ⋮ A path sampling identity for computing the Kullback-Leibler and J divergences ⋮ Adaptive regularisation for ensemble Kalman inversion ⋮ Tuning tempered transitions ⋮ Improving power posterior estimation of statistical evidence ⋮ Recursive pathways to marginal likelihood estimation with prior-sensitivity analysis

Uses Software

• tsbridge

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Tuning tempered transitions
• A Bayesian model selection method with applications
• A path sampling identity for computing the Kullback-Leibler and J divergences
• Local Adaptive Importance Sampling for Multivariate Densities With Strong Nonlinear Relationships
• Sequential Monte Carlo Samplers
• Population-Based Reversible Jump Markov Chain Monte Carlo
• Marginal Likelihood Estimation via Power Posteriors
• Nonparametric Importance Sampling
• Estimating Bayes Factors via Posterior Simulation With the Laplace-Metropolis Estimator
• Real-Parameter Evolutionary Monte Carlo With Applications to Bayesian Mixture Models
• Bayes Factors
• Adaptive importance sampling in monte carlo integration
• Exact Bayesian Inference and Model Selection for Stochastic Models of Epidemics Among a Community of Households
• On Information and Sufficiency
• Simulating normalizing constants: From importance sampling to bridge sampling to path sampling

This page was built for publication: A path sampling identity for computing the Kullback-Leibler and J divergences