Identifiability of latent coordinates and drift-Jacobian graph in additive-noise SDEs is established via pairwise distinct coordinate-wise diffusion variance ratios across two environments.
arXiv preprint arXiv:2410.22729 , year=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
Structural identifiability analysis shows point sources restore identifiability for inferring spatial stochastic dynamics parameters from static snapshots, unlike distributed sources, with limits depending on modeling choices.
Wasserstein Lagrangian Mechanics formalizes second-order dynamics in Wasserstein space and provides an algorithm to learn them from observed marginals without specifying the Lagrangian, outperforming gradient flows on various dynamics.
Derives an explicit risk bound for a diffusion-based drift estimator in SDEs by decomposing error into Euler-Maruyama discretization, score approximation, noise initialization, and sampling variance.
citing papers explorer
-
Disentangling Continuous-Time Latent Dynamics: Identifiability of Latent SDEs via Diffusion Shifts
Identifiability of latent coordinates and drift-Jacobian graph in additive-noise SDEs is established via pairwise distinct coordinate-wise diffusion variance ratios across two environments.
-
Identifiability Limits of Physics-Informed Inference for Spatial Stochastic Dynamics from Static Snapshots
Structural identifiability analysis shows point sources restore identifiability for inferring spatial stochastic dynamics parameters from static snapshots, unlike distributed sources, with limits depending on modeling choices.
-
A Call to Lagrangian Action: Learning Population Mechanics from Temporal Snapshots
Wasserstein Lagrangian Mechanics formalizes second-order dynamics in Wasserstein space and provides an algorithm to learn them from observed marginals without specifying the Lagrangian, outperforming gradient flows on various dynamics.
-
Error Bounds for a Diffusion Model-Based Drift Estimator
Derives an explicit risk bound for a diffusion-based drift estimator in SDEs by decomposing error into Euler-Maruyama discretization, score approximation, noise initialization, and sampling variance.