Towards Identifiability of Interventional Stochastic Differential Equations
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 26 of its 59 references that are in the map. First posted on arXiv 21 May 2025.
Builds on
26 of 59 references.
References · 26
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
- 2018DAGs with NO TEARS: Continuous Optimization for Structure Learningcited by 752
- 2021Maximum Likelihood Training of Score-Based Diffusion Modelscited by 672
- 2020Differentiable Causal Discovery from Interventional Datacited by 218
- 2021Neural SDEs as Infinite-Dimensional GANscited by 161
- 2021Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICAcited by 160
- 2015A Complete Recipe for Stochastic Gradient MCMCcited by 146
- 2023Learning Linear Causal Representations from Interventions under General Nonlinear Mixingcited by 92
- 2022Linear Causal Disentanglement via Interventionscited by 84
- 2023Identifiability Guarantees for Causal Disentanglement from Soft Interventionscited by 84
- 2019Minimum Stein Discrepancy Estimatorscited by 57
14 more
- 2019Scaling structural learning with NO-BEARS to infer causal transcriptome networkscited by 39
- 2019Learning Activation Functions: A new paradigm for understanding Neural Networkscited by 34
- 2020Causal models for dynamical systemscited by 34
- 2022Active Learning for Optimal Intervention Design in Causal Modelscited by 31
- 2023DynGFN: Towards Bayesian Inference of Gene Regulatory Networks with GFlowNetscited by 27
- 2020On Low Rank Directed Acyclic Graphs and Causal Structure Learningcited by 23
- 2023Causal Modeling with Stationary Diffusionscited by 19
- 2024Identifying Drift, Diffusion, and Causal Structure from Temporal Snapshotscited by 13
- 2019A simple and efficient architecture for trainable activation functionscited by 10
- 2013Uniqueness of Tensor Decompositions with Applications to Polynomial Identifiabilitycited by 9
- 2020Graphical continuous Lyapunov modelscited by 9
- 2023An Interventional Perspective on Identifiability in Gaussian LTI Systems with Independent Component Analysiscited by 9
- 2023Generator Identification for Linear SDEs with Additive and Multiplicative Noisecited by 7
- 2025Interpretable Neural ODEs for Gene Regulatory Network Discovery under Perturbationscited by 6
Built on by
Citing papers per year: 2026: 1.
1 paper.