Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Efficient estimators for likelihood ratio sensitivity indices of complex stochastic dynamics

Journal Article · · Journal of Chemical Physics
DOI:https://doi.org/10.1063/1.4943388· OSTI ID:1470323
 [1];  [2];  [2]
  1. Univ. of Massachusetts, Amherst, MA (United States); ETH Zurich, Zurich (Switzerland); Univ. of Massachusetts, Amherst, MA (United States)
  2. Univ. of Massachusetts, Amherst, MA (United States)
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.
Research Organization:
Univ. of Massachusetts, Amherst, MA (United States)
Sponsoring Organization:
USDOE; USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR) (SC-21)
Grant/Contract Number:
SC0010723
OSTI ID:
1470323
Alternate ID(s):
OSTI ID: 1241424
OSTI ID: 22660774
Journal Information:
Journal of Chemical Physics, Journal Name: Journal of Chemical Physics Journal Issue: 10 Vol. 144; ISSN JCPSA6; ISSN 0021-9606
Publisher:
American Institute of Physics (AIP)Copyright Statement
Country of Publication:
United States
Language:
English

References (21)

Applications of Malliavin calculus to Monte Carlo methods in finance journal August 1999
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
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
Multiple positive and negative regulators of signaling by the EGF-receptor journal April 1999
Oscillations and variability in the p53 system journal January 2006
A pathwise derivative approach to the computation of parameter sensitivities in discrete stochastic chemical systems journal January 2012
Steady-state parameter sensitivity in stochastic modeling via trajectory reweighting journal March 2012
Comparison of finite difference based methods to obtain sensitivities of stochastic chemical kinetic models journal February 2013
Goal-oriented sensitivity analysis for lattice kinetic Monte Carlo simulations journal March 2014
Hybrid pathwise sensitivity methods for discrete stochastic models of chemical reaction systems journal January 2015
Stochastic averaging and sensitivity analysis for two scale reaction networks journal February 2016
Quantification of Short Term Signaling by the Epidermal Growth Factor Receptor journal October 1999
A simple framework to justify linear response theory journal March 2010
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
Path-Space Information Bounds for Uncertainty Quantification and Sensitivity Analysis of Stochastic Dynamics journal January 2016
Likelilood ratio gradient estimation: an overview conference January 1987
Likelihood ratio gradient estimation for stochastic systems journal October 1990
Accelerated Sensitivity Analysis in High-Dimensional Stochastic Reaction Networks journal July 2015

Cited By (4)

Girsanov reweighting for path ensembles and Markov state models journal June 2017
Acceleration and sensitivity analysis of lattice kinetic Monte Carlo simulations using parallel processing and rate constant rescaling journal October 2017
Estimation of the infinitesimal generator by square-root approximation journal October 2018
Estimation of the infinitesimal generator by square-root approximation text January 2017

Similar Records

Efficient estimators for likelihood ratio sensitivity indices of complex stochastic dynamics
Journal Article · Mon Mar 14 00:00:00 EDT 2016 · Journal of Chemical Physics · OSTI ID:22660774

Accelerated Sensitivity Analysis in High-Dimensional Stochastic Reaction Networks
Journal Article · Thu Jul 09 20:00:00 EDT 2015 · PLoS ONE · OSTI ID:1456883

Uncertainty quantification for generalized Langevin dynamics
Journal Article · Tue Dec 13 19:00:00 EST 2016 · Journal of Chemical Physics · OSTI ID:1465368