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.
By Arthur Bizzi, Olga Fink
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.
By Saber Salehkaleybar
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...
By Julien Boussard, Antoine D\'{e}bouchage, Th\'{e}o Saulus
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.
By Joanna Zou, Han Cheng Lie, Youssef Marzouk
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.
By Luc Brogat-Motte, Riccardo Bonalli, Alessandro Rudi
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.
By Zhengyi Guo, Wenpin Tang, Renyuan Xu
The paper introduces a new class of stochastic differential equations (SDEs) whose solutions are guaranteed to stay within a specified compact polyhedral state space, addressing key limitations of existing SDE models for irregular, noisy, and partially observed ecological momentary assessment (EMA) data. It demonstrates that traditional chain‑rule constructions fail both theoretically and empirically, derives necessary constraints on drift and diffusion terms, and presents a parameterization that transforms arbitrary dynamics into constraint‑satisfying SDEs. Experiments on several real EMA datasets, including a large suicide‑risk study, show that this approach improves forecasting and optimization compared to standard latent neural SDE baselines, thereby enabling more trustworthy continuous‑time models for clinical time series.
By Malinda Lu, Yue-Jane Liu, Matthew K. Nock, Yaniv Yacoby
arXiv:2606. 11156v1 Announce Type: cross Abstract: Recent one-step generative models accelerate sampling by learning deterministic flow maps of the underlying dynamics.
By Zhengkai Pan, Peter Potaptchik, Wenxi Yao, Michael S. Albergo, Jakiw Pidstrigach
arXiv:2604. 08580v2 Announce Type: replace-cross Abstract: Reward fine-tuning of diffusion and flow models and sampling from tilted or Boltzmann distributions can both be formulated as stochastic optimal control (SOC) problems, where learning an optimal generative dynamics corresponds to optimizing a control under SDE constraints.
By Carles Domingo-Enrich, Jiequn Han
arXiv:2606. 01086v1 Announce Type: cross Abstract: Flow and diffusion models generate high-quality samples in many modalities; however, many network evaluations are required during inference due to numerical integration of an underlying differential equation.
By Sam McCallum, Zander W. Blasingame, Timothy Herschell, Niklas Rindtorff, Alexander Tong, James Foster
arXiv:2606. 28228v1 Announce Type: new Abstract: Causal representation learning for time series has developed strong identifiability results in discrete-time latent causal models, but identifiability in continuous-time latent stochastic differential equation (SDE) models remains largely open.
By Yuanyuan Wang, Wenjie Wang, Haoxuan Li, Mingming Gong, Kun Zhang
arXiv:2404. 05185v4 Announce Type: replace-cross Abstract: This paper deals with a class of neural SDEs and studies the limiting behavior of the associated sampled optimal control problems as the sample size grows to infinity.
By Huafu Liao, Alp\'ar R. M\'esz\'aros, Chenchen Mou, Chao Zhou