arXiv：cs.LG（机器学习，全量分类）· Julien Boussard, Antoine Debouchage, Th\'{e}o Saulus·· 5 小时前AI 评分31
延迟物理系统的驱动因素与动力学可辨识性保证
Identifiability Guarantees for Drivers and Dynamics of Delayed Physical Systems
AI 导读
研究者提出一种有理论支撑的方法，证明在一组宽松假设下，随机延迟微分方程的结构驱动因素与漂移项是可辨识的。该方法在驱动因素可辨识性基准上优于物理信息神经网络、符号回归和因果发现等已有方法，并在第二个评估所学动力学物理一致性的基准上同样表现更优。
正文
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.
| Comments: | 46 pages, 2 figures |
| Subjects: | Machine Learning (stat.ML); Machine Learning (cs.LG); Dynamical Systems (math.DS) |
| Cite as: | arXiv:2609.37944 [stat.ML] |
| (or arXiv:2609.37944v3 [stat.ML] for this version) | |
| https://doi.org/10.48550/arXiv.2609.37944 arXiv-issued DOI via DataCite |
Submission history
From: Julien Boussard [view email]
[v1]
Tue, 29 Sep 2026 16:22:19 UTC (3,592 KB)
[v2]
Wed, 30 Sep 2026 14:00:18 UTC (3,592 KB)
[v3]
Thu, 1 Oct 2026 17:33:44 UTC (3,592 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org