Research map / Probabilistic and scientific modeling / Differential equations and PDEs
Physics-Informed Deep Learning and Compressive Collocation for High-Dimensional Diffusion-Reaction Equations: Practical Existence Theory and Numerics
Simone Brugiapaglia, Nick Dexter, Samir Karam, Weiqi Wang
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 |
|---|---|---|---|
| increase dimension from d=6 to d=20 at fixed m=3000 (ablation) | Periodic PINN · Example 1 | relative L2-error | Hurt |
| increase samples to 10000 (ablation) | Periodic PINN · Example 1, d=6,10,20 | relative L2-error | Improved |
| increase periodic layer nodes beyond 10 (ablation) | Periodic PINN · Example 3, d=6 | relative L2-error | No clear effect |
| add more hidden layers to fully connected part (ablation) | Periodic PINN · Example 3, d=6 | relative L2-error | No clear effect |
| use adaptive lower OMP instead of traditional OMP (ablation) | Compressive Fourier collocation · Examples 2 and 3, d=6 | relative L2-error | Improved |
| use adaptive lower OMP instead of traditional OMP (ablation) | Compressive Fourier collocation · Example 1, d=6 | relative L2-error | Hurt |
| use CFC instead of periodic PINN | High-dim PDE solver · Examples 2-3, d=30 | relative L2-error: gaining from 1 to 8 orders of magnitude | Improved |
| add l1 regularization on last layer (ablation) | Periodic PINN · Examples 1-3, d=10 | relative L2-error | No clear effect |
| freeze first layer as Fourier features with M=16, 32 (ablation) | Periodic PINN · Example 3, d=6, m=10000 | relative L2-error | Improved |
| freeze first layer as Fourier features with M=64 (ablation) | Periodic PINN · Example 3, d=6, m=10000 | relative L2-error | Hurt |
Closest papers by meaning
- Text2PDE: Latent Diffusion Models for Accessible Physics Simulation (ICLR 2025 · similarity 0.90)
- Adversarial Adaptive Sampling: Unify PINN and Optimal Transport for the Approximation of PDEs (ICLR 2024 · similarity 0.89)
- CALM-PDE: Continuous and Adaptive Convolutions for Latent Space Modeling of Time-dependent PDEs (NeurIPS 2025 · similarity 0.88)
- A Unified Sampling Framework for Solver Searching of Diffusion Probabilistic Models (ICLR 2024 · similarity 0.88)
- S4S: Solving for a Fast Diffusion Model Solver (ICML 2025 · similarity 0.88)
- Physics-Informed DeepONets for drift-diffusion on metric graphs: simulation and parameter identification (ICML 2025 · similarity 0.88)
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.
