Efficient computational strategies for doubly intractable problems with applications to Bayesian social networks
From MaRDI portal
Publication:5963546
DOI10.1007/S11222-014-9516-7zbMATH Open1331.62127OpenAlexW1983981363MaRDI QIDQ5963546FDOQ5963546
Abstract: Powerful ideas recently appeared in the literature are adjusted and combined to design improved samplers for Bayesian exponential random graph models. Different forms of adaptive Metropolis-Hastings proposals (vertical, horizontal and rectangular) are tested and combined with the Delayed rejection (DR) strategy with the aim of reducing the variance of the resulting Markov chain Monte Carlo estimators for a given computational time. In the examples treated in this paper the best combination, namely horizontal adaptation with delayed rejection, leads to a variance reduction that varies between 92% and 144% relative to the adaptive direction sampling approximate exchange algorithm of Caimo and Friel (2011). These results correspond to an increased performance which varies from 10% to 94% if we take simulation time into account. The highest improvements are obtained when highly correlated posterior distributions are considered.
Recommendations
- Bayesian analysis for exponential random graph models using the adaptive exchange sampler
- Approximate Bayesian computation for exponential random graph models for large social networks
- Auxiliary parameter MCMC for exponential random graph models
- A note on parallel sampling in Markov graphs
- On Russian roulette estimates for Bayesian inference with doubly-intractable likelihoods
Cites Work
- scientific article; zbMATH DE number 3513115 (Why is no real title available?)
- A note on Metropolis-Hastings kernels for general state spaces
- An adaptive Metropolis algorithm
- Analysing exponential random graph (p-star) models with missing data using Bayesian data augmentation
- Convergence of adaptive direction sampling
- Coupling and Ergodicity of Adaptive Markov Chain Monte Carlo Algorithms
- Delayed rejection in reversible jump Metropolis-Hastings.
- Learn from thy neighbor: parallel-chain and regional adaptive MCMC
- Markov chains for exploring posterior distributions. (With discussion)
- On Metropolis-Hastings algorithms with delayed rejection
- On adaptive Markov chain Monte Carlo algorithms
- On the containment condition for adaptive Markov chain Monte Carlo algorithms
- On the efficiency of adaptive MCMC algorithms
- On the ergodicity properties of some adaptive MCMC algorithms
- Optimal Scaling of Discrete Approximations to Langevin Diffusions
- Optimal scaling for various Metropolis-Hastings algorithms.
- Optimum Monte-Carlo sampling using Markov chains
- Ordering and improving the performance of Monte Carlo Markov chains.
- Weak convergence and optimal scaling of random walk Metropolis algorithms
Cited In (9)
- Bayesian analysis for exponential random graph models using the adaptive exchange sampler
- Equation-solving estimator based on the general n-step MHDR algorithm
- Exponential-family models of random graphs: inference in finite, super and infinite population scenarios
- Model comparison for Gibbs random fields using noisy reversible jump Markov chain Monte Carlo
- Approximate Bayesian computation for exponential random graph models for large social networks
- A multilayer exponential random graph modelling approach for weighted networks
- Stability of doubly-intractable distributions
- Exploiting multi-core architectures for reduced-variance estimation with intractable likelihoods
- Bayesian Model Selection for Exponential Random Graph Models via Adjusted Pseudolikelihoods
This page was built for publication: Efficient computational strategies for doubly intractable problems with applications to Bayesian social networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5963546)
