Parallel Machine Learning for Forecasting the Dynamics of Complex Networks.

Journal: Physical review letters
Published Date:

Abstract

Forecasting the dynamics of large, complex, sparse networks from previous time series data is important in a wide range of contexts. Here we present a machine learning scheme for this task using a parallel architecture that mimics the topology of the network of interest. We demonstrate the utility and scalability of our method implemented using reservoir computing on a chaotic network of oscillators. Two levels of prior knowledge are considered: (i) the network links are known, and (ii) the network links are unknown and inferred via a data-driven approach to approximately optimize prediction.

Authors

  • Keshav Srinivasan
    University of Maryland, College Park, Maryland 20742, USA.
  • Nolan Coble
    University of Maryland, College Park, Maryland 20742, USA.
  • Joy Hamlin
    Stony Brook University, Long Island, New York 11794, USA.
  • Thomas Antonsen
    University of Maryland, College Park, Maryland 20742, USA.
  • Edward Ott
    Institute for Research in Electronics and Applied Physics, University of Maryland, College Park, Maryland 20742, USA.
  • Michelle Girvan
    Institute for Research in Electronics and Applied Physics, University of Maryland, College Park, Maryland 20742, USA.