Towards Identifiability of Interventional Stochastic Differential Equations
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914159449341952 |
|---|---|
| author | Zweig, Aaron Lin, Zaikang Azizi, Elham Knowles, David |
| author_facet | Zweig, Aaron Lin, Zaikang Azizi, Elham Knowles, David |
| contents | We study identifiability of stochastic differential equations (SDE) under multiple interventions. Our results give the first provable bounds for unique recovery of SDE parameters given samples from their stationary distributions. We give tight bounds on the number of necessary interventions for linear SDEs, and upper bounds for nonlinear SDEs in the small noise regime. We experimentally validate the recovery of true parameters in synthetic data, and motivated by our theoretical results, demonstrate the advantage of parameterizations with learnable activation functions in application to gene regulatory dynamics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_15987 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Identifiability of Interventional Stochastic Differential Equations Zweig, Aaron Lin, Zaikang Azizi, Elham Knowles, David Machine Learning We study identifiability of stochastic differential equations (SDE) under multiple interventions. Our results give the first provable bounds for unique recovery of SDE parameters given samples from their stationary distributions. We give tight bounds on the number of necessary interventions for linear SDEs, and upper bounds for nonlinear SDEs in the small noise regime. We experimentally validate the recovery of true parameters in synthetic data, and motivated by our theoretical results, demonstrate the advantage of parameterizations with learnable activation functions in application to gene regulatory dynamics. |
| title | Towards Identifiability of Interventional Stochastic Differential Equations |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2505.15987 |