Research map / Probabilistic and scientific modeling / Differential equations and PDEs
Learning Partial Differential Equations in Reproducing Kernel Hilbert Spaces
George Stepaniants
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 |
|---|---|---|---|
| use Matern 3/2 RKHS kernel instead of exponential or squared exponential kernel (ablation) | RKHS Green's function estimator · 1D Poisson equation | relative error of learned Green's function | Improved |
| set kernel lengthscale sigma = 2/m for mesh size m (ablation) | RKHS Green's function estimator · 1D Poisson and Helmholtz (omega = 20) | relative error | Improved |
| increase number of input-output samples n from 1 to 100 (ablation) | RKHS Green's function estimator · 1D Helmholtz (omega = 20) | relative error | Improved |
| increase mesh discretization m from 1 to 100 (ablation) | RKHS Green's function estimator · 1D Helmholtz (omega = 20) | relative error | Improved |
| increase additive Gaussian noise fraction p from 0% to 50% (ablation) | RKHS Green's function estimator · 1D Helmholtz (omega = 20) | relative error | Hurt |
Closest papers by meaning
- Toward Efficient Kernel-Based Solvers for Nonlinear PDEs (ICML 2025 · similarity 0.88)
- Generalization Error Bounds for Picard-Type Operator Learning in Nonlinear Parabolic PDEs (NeurIPS 2026 · similarity 0.88)
- Neural Green’s Functions (NeurIPS 2025 · similarity 0.87)
- SBNO : Schrödinger Bridge Neural Operator for the Forward and Inverse Problems under Missing Information (NeurIPS 2026 · similarity 0.86)
- Learning the Infinitesimal Generator of Stochastic Diffusion Processes (NeurIPS 2024 · similarity 0.86)
- Guided Diffusion Sampling on Function Spaces with Applications to PDEs (NeurIPS 2025 · similarity 0.86)
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.
