Research map / Probabilistic and scientific modeling / Differential equations and PDEs
Neural Conservation Laws: A Divergence-Free Perspective
Jack Richter-Powell, Yaron Lipman, Ricky T. Q. Chen
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| enforce continuity equation exactly via divergence-free [rho, rho u] parameterization instead of curl parameterization with separate density network (ablation) | neural Euler solver · 3D unit ball variable-density incompressible flow | density advection accuracy | Improved |
| replace PINN penalty on continuity equation with exact NCL parameterization | neural Euler solver · flat torus T^2 incompressible variable density flow | fidelity to FEM reference dynamics | Improved |
| learn Hodge decomposition with divergence-free model in dimensions 25, 50, 100 | NCL · synthetic Hodge decomposition on T^n | squared L2 error to ground truth | Improved |
| use NCL dynamical OT instead of minimax formulation | Wasserstein distance estimation · 2D density pairs (Circles, Pinwheel, 8Gaussians) | estimated squared Wasserstein distance | Improved |
| modify loss terms to avoid division by rho (ablation) | NCL fluid training · Euler equations | training stability | Improved |
Closest papers by meaning
- Harnessing the Power of Neural Operators with Automatically Encoded Conservation Laws (ICML 2024 · similarity 0.88)
- Riemann Tensor Neural Networks: Learning Conservative Systems with Physics-Constrained Networks (ICML 2025 · similarity 0.87)
- Keep the Momentum: Conservation Laws beyond Euclidean Gradient Flows (ICML 2024 · similarity 0.87)
- Neural Conjugate Flows: A Physics-Informed Architecture with Flow Structure (AAAI 2025 · similarity 0.85)
- Hamiltonian Neural PDE Solvers through Functional Approximation (NeurIPS 2025 · similarity 0.85)
- Transformative or Conservative? Conservation laws for ResNets and Transformers (ICML 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
