mlsanityData to 14 Oct 2026

Reflected diffusion, no-flux continuity equations and confined Lagrangian flows in bounded domains

arXiv 2607.28344 ↗First posted 30 Jul 2026math.CA cs.LG math.APcited by 1

Not on the map. Why?

Abstract (arXiv)

Motivated by marginal distribution flows of reflected diffusions in bounded domains, we investigate when a density/flux pair solving a no-flux continuity equation admits a regular Lagrangian flow that remains in the closed domain and generates the prescribed density flow. We give sufficient conditions in terms of interior bounded-variation regularity, bounded-variation control on a boundary collar, a one-sided bound on an absolutely continuous divergence, and vanishing normal trace of the velocity. The proof uses the fact that tangency removes the singular boundary contribution to the divergence of the zero extension, thereby making the extended velocity admissible for the Ambrosio-DiPerna-Lions theory. We show that these boundary assumptions cannot be jointly relaxed so as to admit a boundary current mechanism. We construct an explicit smooth density/flux pair carrying a boundary current. Its density evolution is unique in a weighted class and its characteristics are unique, confined and transport the marginals, yet it admits no regular Lagrangian flow because the compressibility bound fails arbitrarily close to the initial time. We also establish two uniqueness results for no-flux Fokker-Planck equations: a duality result for bounded measurable drifts and a weighted energy result for entrance-type drifts singular at the boundary. Our results provide a rigorous mathematical justification for using the ODE-based sampling of reflected diffusion models under minimal regularity assumptions on the coefficients, and also indicate when such ODE-based samplers may fail.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 4 of its 40 references that are in the map. First posted on arXiv 30 Jul 2026.

Builds on

4 of 40 references.

References · 4

  1. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  2. 2021Maximum Likelihood Training of Score-Based Diffusion Modelscited by 672
  3. 2023Reflected Diffusion Modelscited by 87
  4. 2023Diffusion Models for Constrained Domainscited by 63

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

Similar, not cited

Close in wording, no citation either way

  1. 2026Some remarks on the connection between generative diffusion and optimal transport
  2. 2026The Geometry Behind Diffusion and Flow Matching: Gradient Flows and Geodesics in Wasserstein Space
  3. 2025Optimal Boundary Control of Diffusion on Graphs via Linear Programming
  4. 2026Steering Dynamical Regimes of Diffusion Models by Breaking Detailed Balance
  5. 2026Learning Flow Distributions via Projection-Constrained Diffusion on Manifolds
  6. 2026Noise scheduling and linear dynamics in diffusion models on Lie groups
  7. 2024Reflected Schr"odinger Bridge for Constrained Generative Modeling
  8. 2022Convergence Rates for Regularized Optimal Transport via Quantization