Efficient estimators for likelihood ratio sensitivity indices of complex stochastic dynamics

Abstract

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 algorithms without additional modifications.

Revision of the paper. Added a new estimator

References in corpus (3)

• A Relative Entropy Rate Method for Path Space Sensitivity Analysis of Stationary Complex Stochastic Dynamics
• Accelerated Sensitivity Analysis in High-Dimensional Stochastic Reaction Networks
• Stochastic Averaging and Sensitivity Analysis for Two Scale Reaction Networks

Cited by in corpus (5)

• Girsanov reweighting for path ensembles and Markov state models
• Estimation of the infinitesimal generator by square-root approximation
• Uncertainty quantification for generalized Langevin dynamics
• Stochastic Averaging and Sensitivity Analysis for Two Scale Reaction Networks
• Steady State Sensitivity Analysis of Continuous Time Markov Chains