View in EDS

APT-MCMC, a C++/Python implementation of Markov Chain Monte Carlo for parameter identification.

Saved in:
Bibliographic Details
Title: APT-MCMC, a C++/Python implementation of Markov Chain Monte Carlo for parameter identification.
Authors: Zhang, Li Ang1, Urbano, Alisa2, Clermont, Gilles1,3,4, Swigon, David5, Banerjee, Ipsita1,4,6, Parker, Robert S.1,3,4,6 rparker@pitt.edu
Source: Computers & Chemical Engineering. Feb2018, Vol. 110, p1-12. 12p.
Subjects: Ordinary differential equations, Markov chain Monte Carlo, Computer simulation, C++, Python programming language, Parameter identification
Abstract: The inverse problem associated with fitting parameters of an ordinary differential equation (ODE) system to data is nonlinear and multimodal, which is of great challenge to gradient-based optimizers. Markov Chain Monte Carlo (MCMC) techniques provide an alternative approach to solving these problems and can escape local minima by design. APT-MCMC was created to allow users to setup ODE simulations in Python and run as compiled C++ code. It combines affine-invariant ensemble of samplers and parallel tempering MCMC techniques to improve the simulation efficiency. Simulations use Bayesian inference to provide probability distributions of parameters, which enable analysis of multiple minima and parameter correlation. Benchmark tests result in a 20×–60× speedup but 14% increase in memory usage against emcee , a similar MCMC package in Python. Several MCMC hyperparameters were analyzed: number of temperatures, ensemble size, step size, and swap attempt frequency. Heuristic tuning guidelines are provided for setting these hyperparameters. [ABSTRACT FROM AUTHOR]
Copyright of Computers & Chemical Engineering is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 127671767
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: APT-MCMC, a C++/Python implementation of Markov Chain Monte Carlo for parameter identification.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Zhang%2C+Li+Ang%22">Zhang, Li Ang</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AR" term="%22Urbano%2C+Alisa%22">Urbano, Alisa</searchLink><relatesTo>2</relatesTo><br /><searchLink fieldCode="AR" term="%22Clermont%2C+Gilles%22">Clermont, Gilles</searchLink><relatesTo>1,3,4</relatesTo><br /><searchLink fieldCode="AR" term="%22Swigon%2C+David%22">Swigon, David</searchLink><relatesTo>5</relatesTo><br /><searchLink fieldCode="AR" term="%22Banerjee%2C+Ipsita%22">Banerjee, Ipsita</searchLink><relatesTo>1,4,6</relatesTo><br /><searchLink fieldCode="AR" term="%22Parker%2C+Robert+S%2E%22">Parker, Robert S.</searchLink><relatesTo>1,3,4,6</relatesTo><i> rparker@pitt.edu</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Computers+%26+Chemical+Engineering%22">Computers & Chemical Engineering</searchLink>. Feb2018, Vol. 110, p1-12. 12p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Ordinary+differential+equations%22">Ordinary differential equations</searchLink><br /><searchLink fieldCode="DE" term="%22Markov+chain+Monte+Carlo%22">Markov chain Monte Carlo</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+simulation%22">Computer simulation</searchLink><br /><searchLink fieldCode="DE" term="%22C%2B%2B%22">C++</searchLink><br /><searchLink fieldCode="DE" term="%22Python+programming+language%22">Python programming language</searchLink><br /><searchLink fieldCode="DE" term="%22Parameter+identification%22">Parameter identification</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: The inverse problem associated with fitting parameters of an ordinary differential equation (ODE) system to data is nonlinear and multimodal, which is of great challenge to gradient-based optimizers. Markov Chain Monte Carlo (MCMC) techniques provide an alternative approach to solving these problems and can escape local minima by design. APT-MCMC was created to allow users to setup ODE simulations in Python and run as compiled C++ code. It combines affine-invariant ensemble of samplers and parallel tempering MCMC techniques to improve the simulation efficiency. Simulations use Bayesian inference to provide probability distributions of parameters, which enable analysis of multiple minima and parameter correlation. Benchmark tests result in a 20×–60× speedup but 14% increase in memory usage against emcee , a similar MCMC package in Python. Several MCMC hyperparameters were analyzed: number of temperatures, ensemble size, step size, and swap attempt frequency. Heuristic tuning guidelines are provided for setting these hyperparameters. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Computers & Chemical Engineering is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=127671767
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1016/j.compchemeng.2017.11.011
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 12
        StartPage: 1
    Subjects:
      – SubjectFull: Ordinary differential equations
        Type: general
      – SubjectFull: Markov chain Monte Carlo
        Type: general
      – SubjectFull: Computer simulation
        Type: general
      – SubjectFull: C++
        Type: general
      – SubjectFull: Python programming language
        Type: general
      – SubjectFull: Parameter identification
        Type: general
    Titles:
      – TitleFull: APT-MCMC, a C++/Python implementation of Markov Chain Monte Carlo for parameter identification.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Zhang, Li Ang
      – PersonEntity:
          Name:
            NameFull: Urbano, Alisa
      – PersonEntity:
          Name:
            NameFull: Clermont, Gilles
      – PersonEntity:
          Name:
            NameFull: Swigon, David
      – PersonEntity:
          Name:
            NameFull: Banerjee, Ipsita
      – PersonEntity:
          Name:
            NameFull: Parker, Robert S.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 02
              M: 02
              Text: Feb2018
              Type: published
              Y: 2018
          Identifiers:
            – Type: issn-print
              Value: 00981354
          Numbering:
            – Type: volume
              Value: 110
          Titles:
            – TitleFull: Computers & Chemical Engineering
              Type: main
ResultId 1