One Intervention per Component is Enough: Towards Identifiability in Linear Stochastic Dynamics from Steady State
Read the original on arXiv Machine Learning →The paper investigates how to recover the parameters of a multivariate Ornstein-Uhlenbeck process using only steady-state observational and interventional data. It proves that a single intervention per strongly connected component of the drift graph is sufficient to identify all parameters generically, up to a global scaling factor, provided the SCC condensation graph is connected with a single root and certain spectral conditions hold. A recursive learning algorithm and a regularized least-squares estimator are proposed, and experiments confirm the theoretical results.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.