Towards Identifiability of Interventional Stochastic Differential Equations

ICLR 2026 Conference Submission13190 Authors

Keywords: Stochastic differential equation, causal disentanglement, identifiability, intervention

TL;DR: Proof of efficient recover of interventional SDE with low-rank constraint only from stationary distribution

Abstract: 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.

Primary Area: causal reasoning

Submission Number: 13190