Work

Loss formulations for assumption-free neural inference of SDE coefficient functions

Year: 2025

Type: article

Abstract: Stochastic differential equations (SDEs) are one of the most commonly studied probabilistic dynamical systems, and widely used to model complex biological processes. Building upon the previously introduced idea of performing inference of dynamical systems by parametrising their coefficient functions via neural networks, we propose a novel formulation for an optimisation objective that combines simulation-based penalties with pseudo-likelihoods. This greatly improves prediction performance compared to the state-of-the-art, and makes it possible to learn a wide variety of dynamics without any prior assumptions on analytical structure.

Source: npj Systems Biology and Applications

DOI: 10.1038/s41540-025-00500-6

Authors: Marc Vaisband, Valentin von Bornhaupt, Nina Schmid, Izdar Abulizi, Jan Hasenauer

Institutions: University of Bonn, Paracelsus Medical University, Labor für Immunologische und Molekulare Krebsforschung

Language: English

Topic: Gaussian Processes and Bayesian Inference

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $3,490

Funders: Deutsche Forschungsgemeinschaft, Austrian Science Fund, Rheinische Friedrich-Wilhelms-Universität Bonn