Pathwise Sensitivity Analysis in Transient Regimes
The instantaneous relative entropy (IRE) and the corresponding instantaneous Fisher information matrix (IFIM) for transient stochastic processes are presented in this paper. These novel tools for sensitivity analysis of stochastic models serve as an extension of the well known relative entropy rate (RER) and the corresponding Fisher information matrix (FIM) that apply to stationary processes. Three cases are studied here, discrete-time Markov chains, continuous-time Markov chains and stochastic differential equations. A biological reaction network is presented as a demonstration numerical example.
KeywordsMarkov Chain Stochastic Differential Equation Relative Entropy Markov Chain Model Fisher Information Matrix
The work of the authors was supported by the Office of Advanced Scientific Computing Research, U.S. Department of Energy, under Contract No. DE-SC0010723 and by the European Union (European Social Fund) and Greece (National Strategic Reference Framework), under the THALES Program, grant AMOSICSS.
- 2.DiStefano III J (2013) Dynamic systems biology modeling and simulation. Elsevier, New YorkGoogle Scholar
- 4.Nakayama M, Goyal A, Glynn PW (1994) Likelihood ratio sensitivity analysis for Markovian models of highly dependable systems. Stoch Models 10:701–717Google Scholar
- 12.Baiesi M, Maes C, Boksenbojm E, Wynants B (2010) Nonequilibrium linear response for markov dynamics, II: Inertial dynamics. J Stat Phys 139:492Google Scholar
- 14.Dupuis P, Katsoulakis MA, Pantazis Y, Plecháč P Sesnitivity bounds and error estimates for stochastic models (in Preparation)Google Scholar
- 15.Arampatzis G, Pantazis Y, Katsoulakis MA Accelerated sensitivity analysis in high-dimensional stochastic reaction networks. Submitted to PLoS ONEGoogle Scholar
- 19.Avellaneda M, Friedman CA, Holmes R, Samperi DJ (1997) Calibrating volatility surfaces via relative-entropy minimization. Soc Sci Res NetwGoogle Scholar
- 22.Abramov RV, Grote MJ, Majda AJ (2005) Information theory and stochastics for multiscale nonlinear systems., CRM monograph series. American Mathematical Society, ProvidenceGoogle Scholar
- 24.Oksendal B (2000) Stochastic differential equations: an introduction with applications. Springer, New YorkGoogle Scholar
- 25.Tsourtis A, Pantazis Y, Harmandaris V, Katsoulakis MA Parametric sensitivity analysis for stochastic molecular systems using information theoretic metrics. Submitted to J Chem PhysGoogle Scholar
- 30.Casella G, Berger RL (2002) Statistical inference. Duxbury advanced series in statistics and decision sciencesThomson Learning, LondonGoogle Scholar