Search Menu
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information
Search Scholarly Publications

Title: Efficient estimators for likelihood ratio sensitivity indices of complex stochastic dynamics

Abstract

Here, we demonstrate that centered likelihood ratio estimators for the sensitivity indices of complex stochastic dynamics are highly efficient with low, constant in time variance and consequently they are suitable for sensitivity analysis in long-time and steady-state regimes. These estimators rely on a new covariance formulation of the likelihood ratio that includes as a submatrix a Fisher information matrix for stochastic dynamics and can also be used for fast screening of insensitive parameters and parameter combinations. The proposed methods are applicable to broad classes of stochastic dynamics such as chemical reaction networks, Langevin-type equations and stochastic models in finance, including systems with a high dimensional parameter space and/or disparate decorrelation times between different observables. Furthermore, they are simple to implement as a standard observable in any existing simulation algorithm without additional modifications.

Authors:
 [1];  [2]; ORCiD logo [2]
+ Show Author Affiliations
  1. Univ. of Massachusetts, Amherst, MA (United States); ETH Zurich, Zurich (Switzerland)
  2. Univ. of Massachusetts, Amherst, MA (United States)
Publication Date:
Research Org.:
Univ. of Massachusetts, Amherst, MA (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)
OSTI Identifier:
1470323
Alternate Identifier(s):
OSTI ID: 1241424
Grant/Contract Number:  
SC0010723
Resource Type:
Accepted Manuscript
Journal Name:
Journal of Chemical Physics
Additional Journal Information:
Journal Volume: 144; Journal Issue: 10; Journal ID: ISSN 0021-9606
Publisher:
American Institute of Physics (AIP)
Country of Publication:
United States
Language:
English
Subject:
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY

Citation Formats

Arampatzis, Georgios, Katsoulakis, Markos A., and Rey-Bellet, Luc. Efficient estimators for likelihood ratio sensitivity indices of complex stochastic dynamics. United States: N. p., 2016. Web. doi:10.1063/1.4943388.
Copy to clipboard
Arampatzis, Georgios, Katsoulakis, Markos A., & Rey-Bellet, Luc. Efficient estimators for likelihood ratio sensitivity indices of complex stochastic dynamics. United States. https://doi.org/10.1063/1.4943388
Copy to clipboard
Arampatzis, Georgios, Katsoulakis, Markos A., and Rey-Bellet, Luc. Fri . "Efficient estimators for likelihood ratio sensitivity indices of complex stochastic dynamics". United States. https://doi.org/10.1063/1.4943388. https://www.osti.gov/servlets/purl/1470323.
Copy to clipboard
@article{osti_1470323,
title = {Efficient estimators for likelihood ratio sensitivity indices of complex stochastic dynamics},
author = {Arampatzis, Georgios and Katsoulakis, Markos A. and Rey-Bellet, Luc},
abstractNote = {Here, we demonstrate that centered likelihood ratio estimators for the sensitivity indices of complex stochastic dynamics are highly efficient with low, constant in time variance and consequently they are suitable for sensitivity analysis in long-time and steady-state regimes. These estimators rely on a new covariance formulation of the likelihood ratio that includes as a submatrix a Fisher information matrix for stochastic dynamics and can also be used for fast screening of insensitive parameters and parameter combinations. The proposed methods are applicable to broad classes of stochastic dynamics such as chemical reaction networks, Langevin-type equations and stochastic models in finance, including systems with a high dimensional parameter space and/or disparate decorrelation times between different observables. Furthermore, they are simple to implement as a standard observable in any existing simulation algorithm without additional modifications.},
doi = {10.1063/1.4943388},
journal = {Journal of Chemical Physics},
number = 10,
volume = 144,
place = {United States},
year = {Fri Mar 11 00:00:00 EST 2016},
month = {Fri Mar 11 00:00:00 EST 2016}
}
Copy to clipboard
Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record
https://doi.org/10.1063/1.4943388
Copyright Statement
Other availability
Search WorldCat Search WorldCat to find libraries that may hold this journal
Citation Metrics:
Cited by: 9 works
Citation information provided by
Web of Science
Save / Share:
Export Metadata
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.

Works referenced in this record:

Goal-oriented sensitivity analysis for lattice kinetic Monte Carlo simulations
journal, March 2014

  • Arampatzis, Georgios; Katsoulakis, Markos A.
  • The Journal of Chemical Physics, Vol. 140, Issue 12
  • DOI: 10.1063/1.4868649

Quantification of Short Term Signaling by the Epidermal Growth Factor Receptor
journal, October 1999

  • Kholodenko, Boris N.; Demin, Oleg V.; Moehren, Gisela
  • Journal of Biological Chemistry, Vol. 274, Issue 42
  • DOI: 10.1074/jbc.274.42.30169

SPSens: a software package for stochastic parameter sensitivity analysis of biochemical reaction networks
journal, October 2012

An Efficient Finite Difference Method for Parameter Sensitivities of Continuous Time Markov Chains
journal, January 2012

  • Anderson, David F.
  • SIAM Journal on Numerical Analysis, Vol. 50, Issue 5
  • DOI: 10.1137/110849079

Accelerated Sensitivity Analysis in High-Dimensional Stochastic Reaction Networks
journal, July 2015

A relative entropy rate method for path space sensitivity analysis of stationary complex stochastic dynamics
journal, February 2013

  • Pantazis, Yannis; Katsoulakis, Markos A.
  • The Journal of Chemical Physics, Vol. 138, Issue 5
  • DOI: 10.1063/1.4789612

Path-Space Information Bounds for Uncertainty Quantification and Sensitivity Analysis of Stochastic Dynamics
journal, January 2016

  • Dupuis, Paul; Katsoulakis, Markos A.; Pantazis, Yannis
  • SIAM/ASA Journal on Uncertainty Quantification, Vol. 4, Issue 1
  • DOI: 10.1137/15M1025645

Comparison of finite difference based methods to obtain sensitivities of stochastic chemical kinetic models
journal, February 2013

  • Srivastava, Rishi; Anderson, David F.; Rawlings, James B.
  • The Journal of Chemical Physics, Vol. 138, Issue 7
  • DOI: 10.1063/1.4790650

Likelihood ratio gradient estimation for stochastic systems
journal, October 1990

A pathwise derivative approach to the computation of parameter sensitivities in discrete stochastic chemical systems
journal, January 2012

  • Sheppard, Patrick W.; Rathinam, Muruhan; Khammash, Mustafa
  • The Journal of Chemical Physics, Vol. 136, Issue 3
  • DOI: 10.1063/1.3677230

Applications of Malliavin calculus to Monte Carlo methods in finance
journal, August 1999

  • Fournié, Eric; Lasry, Jean-Michel; Lebuchoux, Jérôme
  • Finance and Stochastics, Vol. 3, Issue 4
  • DOI: 10.1007/s007800050068

Stochastic averaging and sensitivity analysis for two scale reaction networks
journal, February 2016

  • Hashemi, Araz; Núñez, Marcel; Plecháč, Petr
  • The Journal of Chemical Physics, Vol. 144, Issue 7
  • DOI: 10.1063/1.4942008

Oscillations and variability in the p53 system
journal, January 2006

  • Geva‐Zatorsky, Naama; Rosenfeld, Nitzan; Itzkovitz, Shalev
  • Molecular Systems Biology, Vol. 2, Issue 1
  • DOI: 10.1038/msb4100068

Steady-state parameter sensitivity in stochastic modeling via trajectory reweighting
journal, March 2012

  • Warren, Patrick B.; Allen, Rosalind J.
  • The Journal of Chemical Physics, Vol. 136, Issue 10
  • DOI: 10.1063/1.3690092

Likelilood ratio gradient estimation: an overview
conference, January 1987

  • Glynn, Peter W.
  • Proceedings of the 19th conference on Winter simulation - WSC '87
  • DOI: 10.1145/318371.318612

A simple framework to justify linear response theory
journal, March 2010

Hybrid pathwise sensitivity methods for discrete stochastic models of chemical reaction systems
journal, January 2015

  • Wolf, Elizabeth Skubak; Anderson, David F.
  • The Journal of Chemical Physics, Vol. 142, Issue 3
  • DOI: 10.1063/1.4905332

Applications of Malliavin calculus to Monte Carlo methods in finance
journal, August 1999

  • Fournié, Eric; Lasry, Jean-Michel; Lebuchoux, Jérôme
  • Finance and Stochastics, Vol. 3, Issue 4
  • DOI: 10.1007/s007800050068

Multiple positive and negative regulators of signaling by the EGF-receptor
journal, April 1999

A relative entropy rate method for path space sensitivity analysis of stationary complex stochastic dynamics
journal, February 2013

  • Pantazis, Yannis; Katsoulakis, Markos A.
  • The Journal of Chemical Physics, Vol. 138, Issue 5
  • DOI: 10.1063/1.4789612

SPSens: a software package for stochastic parameter sensitivity analysis of biochemical reaction networks
text, January 2013

Accelerated Sensitivity Analysis in High-Dimensional Stochastic Reaction Networks
text, January 2014

    Sort by:
    [ × clear filter / sort ]

    Works referencing / citing this record:

    Girsanov reweighting for path ensembles and Markov state models
    journal, June 2017

    • Donati, L.; Hartmann, C.; Keller, B. G.
    • The Journal of Chemical Physics, Vol. 146, Issue 24
    • DOI: 10.1063/1.4989474

    Acceleration and sensitivity analysis of lattice kinetic Monte Carlo simulations using parallel processing and rate constant rescaling
    journal, October 2017

    • Núñez, M.; Robie, T.; Vlachos, D. G.
    • The Journal of Chemical Physics, Vol. 147, Issue 16
    • DOI: 10.1063/1.4998926

    Estimation of the infinitesimal generator by square-root approximation
    journal, October 2018

    • Donati, Luca; Heida, Martin; Keller, Bettina G.
    • Journal of Physics: Condensed Matter, Vol. 30, Issue 42
    • DOI: 10.1088/1361-648x/aadfc8

    Estimation of the infinitesimal generator by square-root approximation
    text, January 2017

      Sort by:
      [ × clear filter / sort ]

      Similar Records in DOE PAGES and OSTI.GOV collections: