Equi-energy sampler with applications in statistical inference and statistical mechanics
arXiv:math/0507080 · doi:10.1214/009053606000000515
Abstract
We introduce a new sampling algorithm, the equi-energy sampler, for efficient statistical sampling and estimation. Complementary to the widely used temperature-domain methods, the equi-energy sampler, utilizing the temperature--energy duality, targets the energy directly. The focus on the energy function not only facilitates efficient sampling, but also provides a powerful means for statistical estimation, for example, the calculation of the density of states and microcanonical averages in statistical mechanics. The equi-energy sampler is applied to a variety of problems, including exponential regression in statistics, motif sampling in computational biology and protein folding in biophysics.
This paper discussed in: [math.ST/0611217], [math.ST/0611219], [math.ST/0611221], [math.ST/0611222]. Rejoinder in [math.ST/0611224]. Published at http://dx.doi.org/10.1214/009053606000000515 in the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)
Cited by in corpus (49)
- Estimating and understanding exponential random graph models
- Conditions for rapid mixing of parallel and simulated tempering on multimodal distributions
- Convergence of adaptive and interacting Markov chain Monte Carlo algorithms
- Geometric integrators and the Hamiltonian Monte Carlo method
- Coupling and Convergence for Hamiltonian Monte Carlo
- Sequentially interacting Markov chain Monte Carlo methods
- Deterministic Sampling of Expensive Posteriors Using Minimum Energy Designs
- A Repelling-Attracting Metropolis Algorithm for Multimodality
- Stochastic Approximation and Newton's Estimate of a Mixing Distribution
- A Mixture-Based Approach to Regional Adaptation for MCMC
- On nonlinear Markov chain Monte Carlo
- Improving SAMC using smoothing methods: Theory and applications to Bayesian model selection problems
- Coupling hidden Markov models for the discovery of Cis-regulatory modules in multiple species
- Penalized Estimation of Directed Acyclic Graphs From Discrete Data
- Mode jumping MCMC for Bayesian variable selection in GLMM
- Convergence of unadjusted Hamiltonian Monte Carlo for mean-field models
- Sequential Markov Chain Monte Carlo
- Bayesian computation: a perspective on the current state, and sampling backwards and forwards
- A cautionary tale on the efficiency of some adaptive Monte Carlo schemes
- Interacting Markov chain Monte Carlo methods for solving nonlinear measure-valued equations
- Irreversible Samplers from Jump and Continuous Markov Processes
- Convergence rate of Markov chain methods for genomic motif discovery
- Two-scale coupling for preconditioned Hamiltonian Monte Carlo in infinite dimensions
- Accelerating Parallel Tempering: Quantile Tempering Algorithm (QuanTA)
- Warp Bridge Sampling: The Next Generation
- Non-asymptotic Error Bounds for Sequential MCMC Methods in Multimodal Settings
- Multiplicative random walk Metropolis-Hastings on the real line
- Resampling from the past to improve on MCMC algorithms
- Split Sampling: Expectations, Normalisation and Rare Events
- Some Remarks on Replicated Simulated Annealing
- Efficient sampling of non log-concave posterior distributions with mixture of noises
- A Parallel Evolutionary Multiple-Try Metropolis Markov Chain Monte Carlo Algorithm for Sampling Spatial Partitions
- MCMC with Strings and Branes: The Suburban Algorithm (Extended Version)
- Weight-Preserving Simulated Tempering
- Finite Sample Properties of Adaptive Markov Chains via Curvature
- Pseudo-extended Markov chain Monte Carlo
- Equi-Energy sampling does not converge rapidly on the mean-field Potts model with three colors close to the critical temperature
- Adaptive Equi-Energy Sampler : Convergence and Illustration
- Optimal Temperature Spacing for Regionally Weight-preserving Tempering
- Fluctuations of Interacting Markov Chain Monte Carlo Methods
- Improving the convergence of Markov chains via permutations and projections
- Likelihood-Free Parallel Tempering
- Forgetting the starting distribution in finite interacting tempering
- Parallel Tempering with Equi-Energy Moves
- Algorithmic Bayesian Group Gibbs Selection
- Population-Based Reversible Jump Markov Chain Monte Carlo
- Improved annealing for sampling from multimodal distributions via landscape modification
- Reconstructing the energy landscape of a distribution from Monte Carlo samples
- Principle of detailed balance and convergence assessment of Markov Chain Monte Carlo methods and simulated annealing