DRAM: Efficient adaptive MCMC

Authors:
Heikki Haario;Marko Laine;Antonietta Mira;Eero Saksman
Affiliations:
Lappeenranta University of Technology, Lappeenranta, Finland;Lappeenranta University of Technology, Lappeenranta, Finland;University of Insubria, Varese, Italy;University of Jyväaskyläa, Jyväaskyläa, Finland
Venue:
Statistics and Computing
Year:
2006

Citing 0
Cited 17

Bayesian modelling of algal mass occurrences-using adaptive MCMC methods with a lake water quality model

Environmental Modelling & Software
Differential Evolution Markov Chain with snooker updater and fewer chains

Statistics and Computing
Short communication: Grapham: Graphical models with adaptive random walk Metropolis algorithms

Computational Statistics & Data Analysis
Exploring uncertainty and model predictive performance concepts via a modular snowmelt-runoff modeling framework

Environmental Modelling & Software
Hierarchical Bayesian inference for Ill-posed problems via variational method

Journal of Computational Physics
Parameter and State Model Reduction for Large-Scale Statistical Inverse Problems

SIAM Journal on Scientific Computing
A generative approach for image-based modeling of tumor growth

IPMI'11 Proceedings of the 22nd international conference on Information processing in medical imaging
Automating calibration, sensitivity and uncertainty analysis of complex models using the R package Flexible Modeling Environment (FME): SWAT as an example

Environmental Modelling & Software
Parallel hierarchical sampling: A general-purpose interacting Markov chains Monte Carlo algorithm

Computational Statistics & Data Analysis
The parallel c++ statistical library 'QUESO': quantification of uncertainty for estimation, simulation and optimization

Euro-Par'11 Proceedings of the 2011 international conference on Parallel Processing
Bayesian inference with optimal maps

Journal of Computational Physics
Simulation-based optimal Bayesian experimental design for nonlinear systems

Journal of Computational Physics
Using a Bayesian framework and global sensitivity analysis to identify strengths and weaknesses of two process-based models differing in representation of autotrophic respiration

Environmental Modelling & Software
A comparative study of Monte Carlo methods to compute rare event probabilities of failure in reliability models

Proceedings of the 6th ACM India Computing Convention
Component mode synthesis techniques for finite element model updating

Computers and Structures
Proposal adaptation in simulated annealing for continuous optimization problems

Computational Statistics
Low-rank separated representation surrogates of high-dimensional stochastic functions: Application in Bayesian inference

Journal of Computational Physics

Quantified Score

Hi-index	0.02

Visualization

Abstract

We propose to combine two quite powerful ideas that have recently appeared in the Markov chain Monte Carlo literature: adaptive Metropolis samplers and delayed rejection. The ergodicity of the resulting non-Markovian sampler is proved, and the efficiency of the combination is demonstrated with various examples. We present situations where the combination outperforms the original methods: adaptation clearly enhances efficiency of the delayed rejection algorithm in cases where good proposal distributions are not available. Similarly, delayed rejection provides a systematic remedy when the adaptation process has a slow start.