arXiv:2505. 15987v5 Announce Type: replace Abstract: We study identifiability of stochastic differential equations (SDE) under multiple interventions.
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.
arXiv:2607. 19173v1 Announce Type: new Abstract: Neural stochastic differential equations (SDEs) have emerged as powerful tools for learning noisy or stochastic dynamics directly from data; however, existing approaches largely assume uncoupled and continuous noise, limiting their applicability to realistic stochastic drivers, and often scale poorly in time, requiring expensive autoregressive training.
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.
arXiv:2609.37944v1 Announce Type: cross Abstract: A wide range of methods have been proposed, including physics-informed neural networks, which are powerful but do not guarantee identifiability of th...
arXiv:2603. 20467v2 Announce Type: replace-cross Abstract: Stochastic differential equations (SDEs), which serve as the governing equations for dynamical systems in a broad range of applications, can become cost-prohibitive for numerical simulation at scales necessary for quantifying key properties.
arXiv:2411. 01982v2 Announce Type: replace-cross Abstract: We study the problem of learning controlled stochastic differential equations (SDEs) \[ dX_t = b(t,X_t,u_t)\,dt + \sigma(t,X_t,u_t)\,dW_t, \] whose drift and diffusion depend nonlinearly on time, state, and control values.
arXiv:2602. 05533v3 Announce Type: replace Abstract: We study conditional generation in diffusion models under hard constraints, where generated samples must satisfy prescribed events with probability one.