ODIN: ODE-Informed Regression for Parameter and State Inference in Time-Continuous Dynamical Systems

Authors

  • Philippe Wenk ETH Zurich
  • Gabriele Abbati University of Oxford
  • Michael A. Osborne University of Oxford
  • Bernhard Schölkopf Max Planck Institute for Intelligent Systems
  • Andreas Krause ETH Zurich
  • Stefan Bauer MPI IS

DOI:

https://doi.org/10.1609/aaai.v34i04.6106

Abstract

Parameter inference in ordinary differential equations is an important problem in many applied sciences and in engineering, especially in a data-scarce setting. In this work, we introduce a novel generative modeling approach based on constrained Gaussian processes and leverage it to build a computationally and data efficient algorithm for state and parameter inference. In an extensive set of experiments, our approach outperforms the current state of the art for parameter inference both in terms of accuracy and computational cost. It also shows promising results for the much more challenging problem of model selection.

Downloads

Published

2020-04-03

How to Cite

Wenk, P., Abbati, G., Osborne, M. A., Schölkopf, B., Krause, A., & Bauer, S. (2020). ODIN: ODE-Informed Regression for Parameter and State Inference in Time-Continuous Dynamical Systems. Proceedings of the AAAI Conference on Artificial Intelligence, 34(04), 6364-6371. https://doi.org/10.1609/aaai.v34i04.6106

Issue

Section

AAAI Technical Track: Machine Learning