TU Berlin

Methods of Artificial IntelligencePublications

Page Content

to Navigation

List of Publications

Inferring hidden states in Langevin dynamics on large networks: Average case performance
Citation key BrOpSo17
Author Bravi, B. and Opper, M. and Sollich, P.
Pages 012122
Year 2017
ISSN 24700045
DOI https://doi.org/10.1103/PhysRevE.95.012122
Journal Phys. Rev. E
Volume 95
Month Jan
Publisher American Physical Society
Abstract We present average performance results for dynamical inference problems in large networks, where a set of nodes is hidden while the time trajectories of the others are observed. Examples of this scenario can occur in signal transduction and gene regulation networks. We focus on the linear stochastic dynamics of continuous variables interacting via random Gaussian couplings of generic symmetry. We analyze the inference error, given by the variance of the posterior distribution over hidden paths, in the thermodynamic limit and as a function of the system parameters and the ratio α between the number of hidden and observed nodes. By applying Kalman filter recursions we find that the posterior dynamics is governed by an “effective” drift that incorporates the effect of the observations. We present two approaches for characterizing the posterior variance that allow us to tackle, respectively, equilibrium and nonequilibrium dynamics. The first appeals to Random Matrix Theory and reveals average spectral properties of the inference error and typical posterior relaxation times; the second is based on dynamical functionals and yields the inference error as the solution of an algebraic equation.
Download Bibtex entry


Quick Access

Schnellnavigation zur Seite über Nummerneingabe