PreprintCC BY 4.0arXiv
Identifiability Guarantees for Drivers and Dynamics of Delayed Physical Systems
Abstract
A wide range of methods have been proposed, including physics-informed neural networks, which are powerful but do not guarantee identifiability of the dynamics, symbolic regression, which requires a set of precomputed operations, and causal discovery, which is more principled but usually relies on strong assumptions that physical systems may violate. In this work, we develop a theory-grounded method and prove that under a set of permissive assumptions, the structural drivers and drift of stochastic delayed differential equations are identifiable. Our method outperforms others on a benchmark for driver identifiability, and on a second benchmark to evaluate physical consistency of the learned dynamics.
Related
- Adaptive Conformal Inference Under Delayed Feedback: Coverage Guarantees and a Delay-to-Memory Diagnostic
- Bayesian heterogeneous copula mixtures with nonparametric margins: consistency, identifiability and tail asymmetry in physical fitness data
- Theoretical guarantees for stochastic gradient Langevin dynamics
- Statistical and Privacy Guarantees for Deep M-Regression via Stochastic Gradient Langevin Dynamics
- Disentangling Continuous-Time Latent Dynamics: Identifiability of Latent SDEs via Diffusion Shifts
BibTeX
@misc{boussard2026identifiability,
title = {{Identifiability Guarantees for Drivers and Dynamics of Delayed Physical Systems}},
author = {Julien Boussard and Antoine Debouchage and Théo Saulus},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2609.37944},
eprint = {2609.37944},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.37944},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Identifiability Guarantees for Drivers and Dynamics of Delayed Physical Systems
AU - Julien Boussard
AU - Antoine Debouchage
AU - Théo Saulus
PY - 2026
DA - 2026/10/01
PB - arXiv
DO - 10.48550/arxiv.2609.37944
UR - https://arxiv.org/abs/2609.37944
AB - A wide range of methods have been proposed, including physics-informed neural networks, which are powerful but do not guarantee identifiability of the dynamics, symbolic regression, which requires a set of precomputed operations, and causal discovery, which is more principled but usually relies on strong assumptions that physical systems may violate. In this work, we develop a theory-grounded method and prove that under a set of permissive assumptions, the structural drivers and drift of stochastic delayed differential equations are identifiable. Our method outperforms others on a benchmark for driver identifiability, and on a second benchmark to evaluate physical consistency of the learned dynamics.
ER -