SAChES: Scalable Adaptive Chain-Ensemble Sampling.

Swiler, Laura Painton; Ray, Jaideep; Ebeida, Mohamed Salah; Huang, Maoyi; Hou, Zhangshuan; Bao, Jie; Ren, Huiying

doi:10.2172/1380101

Title: SAChES: Scalable Adaptive Chain-Ensemble Sampling.

Full Record
Other Related Research

Abstract

We present the development of a parallel Markov Chain Monte Carlo (MCMC) method called SAChES, Scalable Adaptive Chain-Ensemble Sampling. This capability is targed to Bayesian calibration of com- putationally expensive simulation models. SAChES involves a hybrid of two methods: Differential Evo- lution Monte Carlo followed by Adaptive Metropolis. Both methods involve parallel chains. Differential evolution allows one to explore high-dimensional parameter spaces using loosely coupled (i.e., largely asynchronous) chains. Loose coupling allows the use of large chain ensembles, with far more chains than the number of parameters to explore. This reduces per-chain sampling burden, enables high-dimensional inversions and the use of computationally expensive forward models. The large number of chains can also ameliorate the impact of silent-errors, which may affect only a few chains. The chain ensemble can also be sampled to provide an initial condition when an aberrant chain is re-spawned. Adaptive Metropolis takes the best points from the differential evolution and efficiently hones in on the poste- rior density. The multitude of chains in SAChES is leveraged to (1) enable efficient exploration of the parameter space; and (2) ensure robustness to silent errors which may be unavoidable in extreme-scale computational platforms of the future. This report outlines SAChES,more »« less

Authors:

Swiler, Laura Painton ^[1]; Ray, Jaideep ^[2]; Ebeida, Mohamed Salah ^[1]; Huang, Maoyi ^[3]; Hou, Zhangshuan ^[3]; Bao, Jie ^[3]; Ren, Huiying ^[3]

Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
Sandia National Lab. (SNL-CA), Livermore, CA (United States)
Pacific Northwest National Lab. (PNNL), Richland, WA (United States)

Publication Date:: Tue Aug 01 00:00:00 EDT 2017

Research Org.:: Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)

Sponsoring Org.:: USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)

OSTI Identifier:: 1380101

Report Number(s):: SAND2017-9373
656670

DOE Contract Number:: AC04-94AL85000

Resource Type:: Technical Report

Country of Publication:: United States

Language:: English

Subject:: 97 MATHEMATICS AND COMPUTING

Citation Formats


                    Swiler, Laura Painton, Ray, Jaideep, Ebeida, Mohamed Salah, Huang, Maoyi, Hou, Zhangshuan, Bao, Jie, and Ren, Huiying. SAChES: Scalable Adaptive Chain-Ensemble Sampling..  United States: N. p., 2017. 
        Web.  doi:10.2172/1380101.

Copy to clipboard


                    Swiler, Laura Painton, Ray, Jaideep, Ebeida, Mohamed Salah, Huang, Maoyi, Hou, Zhangshuan, Bao, Jie, & Ren, Huiying. SAChES: Scalable Adaptive Chain-Ensemble Sampling..  United States.  https://doi.org/10.2172/1380101

Copy to clipboard


                    Swiler, Laura Painton, Ray, Jaideep, Ebeida, Mohamed Salah, Huang, Maoyi, Hou, Zhangshuan, Bao, Jie, and Ren, Huiying. 2017.  
        "SAChES: Scalable Adaptive Chain-Ensemble Sampling.".  United States.  https://doi.org/10.2172/1380101.  https://www.osti.gov/servlets/purl/1380101.

Copy to clipboard


                    
@article{osti_1380101,

  title        = {SAChES: Scalable Adaptive Chain-Ensemble Sampling.},

  author       = {Swiler, Laura Painton and Ray, Jaideep and Ebeida, Mohamed Salah and Huang, Maoyi and Hou, Zhangshuan and Bao, Jie and Ren, Huiying},

  abstractNote = {We present the development of a parallel Markov Chain Monte Carlo (MCMC) method called SAChES, Scalable Adaptive Chain-Ensemble Sampling. This capability is targed to Bayesian calibration of com- putationally expensive simulation models. SAChES involves a hybrid of two methods: Differential Evo- lution Monte Carlo followed by Adaptive Metropolis. Both methods involve parallel chains. Differential evolution allows one to explore high-dimensional parameter spaces using loosely coupled (i.e., largely asynchronous) chains. Loose coupling allows the use of large chain ensembles, with far more chains than the number of parameters to explore. This reduces per-chain sampling burden, enables high-dimensional inversions and the use of computationally expensive forward models. The large number of chains can also ameliorate the impact of silent-errors, which may affect only a few chains. The chain ensemble can also be sampled to provide an initial condition when an aberrant chain is re-spawned. Adaptive Metropolis takes the best points from the differential evolution and efficiently hones in on the poste- rior density. The multitude of chains in SAChES is leveraged to (1) enable efficient exploration of the parameter space; and (2) ensure robustness to silent errors which may be unavoidable in extreme-scale computational platforms of the future. This report outlines SAChES, describes four papers that are the result of the project, and discusses some additional results.},

  doi          = {10.2172/1380101},

  url          = {https://www.osti.gov/biblio/1380101},
  journal      = {},
number       = ,

  volume       = ,

  place        = {United States},

  year         = {Tue Aug 01 00:00:00 EDT 2017},

  month        = {Tue Aug 01 00:00:00 EDT 2017}

}

Copy to clipboard

Technical Report:

View Technical Report (7.83 MB)

https://doi.org/10.2172/1380101

Save / Share:

Export Metadata

Save to My Library

Similar records in OSTI.GOV collections:

Bayesian calibration of terrestrial ecosystem models: a study of advanced Markov chain Monte Carlo methods

Journal Article Lu, Dan; Ricciuto, Daniel; Walker, Anthony; ... - Biogeosciences (Online)

Calibration of terrestrial ecosystem models is important but challenging. Bayesian inference implemented by Markov chain Monte Carlo (MCMC) sampling provides a comprehensive framework to estimate model parameters and associated uncertainties using their posterior distributions. The effectiveness and efficiency of the method strongly depend on the MCMC algorithm used. In this work, a differential evolution adaptive Metropolis (DREAM) algorithm is used to estimate posterior distributions of 21 parameters for the data assimilation linked ecosystem carbon (DALEC) model using 14 years of daily net ecosystem exchange data collected at the Harvard Forest Environmental Measurement Site eddy-flux tower. The calibration of DREAM results inmore »« less
Cited by 19
https://doi.org/10.5194/bg-14-4295-2017

Full Text Available
Bayesian calibration of terrestrial ecosystem models: A study of advanced Markov chain Monte Carlo methods

Journal Article Lu, Dan; Ricciuto, Daniel; Walker, Anthony; ... - Biogeosciences Discussions (Online)

Calibration of terrestrial ecosystem models is important but challenging. Bayesian inference implemented by Markov chain Monte Carlo (MCMC) sampling provides a comprehensive framework to estimate model parameters and associated uncertainties using their posterior distributions. The effectiveness and efficiency of the method strongly depend on the MCMC algorithm used. In this study, a Differential Evolution Adaptive Metropolis (DREAM) algorithm was used to estimate posterior distributions of 21 parameters for the data assimilation linked ecosystem carbon (DALEC) model using 14 years of daily net ecosystem exchange data collected at the Harvard Forest Environmental Measurement Site eddy-flux tower. The DREAM is a multi-chainmore »« less
https://doi.org/10.5194/bg-2017-41

Full Text Available
Accelerating Markov chain Monte Carlo simulation by differential evolution with self-adaptive randomized subspace sampling

Journal Article Vrugt, Jasper; Hyman, James; Robinson, Bruce; ... - International Journal of Nonlinear Sciences and Numerical Simulation

Markov chain Monte Carlo (MCMC) methods have found widespread use in many fields of study to estimate the average properties of complex systems, and for posterior inference in a Bayesian framework. Existing theory and experiments prove convergence of well constructed MCMC schemes to the appropriate limiting distribution under a variety of different conditions. In practice, however this convergence is often observed to be disturbingly slow. This is frequently caused by an inappropriate selection of the proposal distribution used to generate trial moves in the Markov Chain. Here we show that significant improvements to the efficiency of MCMC simulation can bemore »« less
Full Text Available
Determining Physical Parameters of Shielded Uranium using Gamma Spectroscopy and the Differential Evolution Adaptive Metropolis (DREAM) Method

Journal Article Knowles, Justin; Bledsoe, Keith; Lefebvre, Jordan; ... - Transactions of the American Nuclear Society

Inverse radiation transport is a well-established method for determining unknown parameters within a system that exhibits particle leakage. Two significant challenges of solving inverse transport problems are (1) to determine multiple unknowns without false convergence on local minima and (2) to be able to quantify uncertainty. It was recently demonstrated that the Differential Evolution Adaptive Metropolis (DREAM) method effectively meets both of these challenges. In Bledsoe's 2014 article, the DREAM method was only applied to numerical test cases in which measured data were simulated using MCNP. This paper provides results of research conducted at Oak Ridge National Laboratory (ORNL) inmore »« less
Bayesian inversion of seismic and electromagnetic data for marine gas reservoir characterization using multi-chain Markov chain Monte Carlo sampling

Journal Article Ren, Huiying; Ray, Jaideep; Hou, Zhangshuan; ... - Journal of Applied Geophysics

In this study we developed an efficient Bayesian inversion framework for interpreting marine seismic amplitude versus angle (AVA) and controlled source electromagnetic (CSEM) data for marine reservoir characterization. The framework uses a multi-chain Markov-chain Monte Carlo (MCMC) sampler, which is a hybrid of DiffeRential Evolution Adaptive Metropolis (DREAM) and Adaptive Metropolis (AM) samplers. The inversion framework is tested by estimating reservoir-fluid saturations and porosity based on marine seismic and CSEM data. The multi-chain MCMC is scalable in terms of the number of chains, and is useful for computationally demanding Bayesian model calibration in scientific and engineering problems. As a demonstration,more »« less
https://doi.org/10.1016/j.jappgeo.2017.10.004

Similar Records