Research map / Probabilistic and scientific modeling / Differential equations and PDEs
Robust Low-Rank Discovery of Data-Driven Partial Differential Equations
Jun Li, Gan Sun, Guoshuai Zhao, Li-wei H. Lehman
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 |
|---|---|---|---|
| add low-rank regression with outlier separation on Ut (DLrSR vs rSGTR) (ablation) | DLrSR · Parametric Burgers, {U,Ut}+noise | coefficient error (%): 832.45845% -> 13.335198% | Improved |
| add low-rank regression with outlier separation on Ut (DLrSR vs rSGTR) (ablation) | DLrSR · Advection-diffusion, {U,Ut}+noise | coefficient error (%): 45.833947% -> 5.2214745% | Improved |
| add low-rank regression with outlier separation on Ut (DLrSR vs rSGTR) (ablation) | DLrSR · Parametric KS, {U,Ut}+noise | coefficient error (%): 16.428652% -> 13.961776% | Improved |
| add rPCA denoising of U before SGTR (ablation) | SGTR · Parametric Burgers, U+noise | coefficient error (%): 6592.7198% -> 6.3265683% | Improved |
| add rPCA denoising of U before STR (ablation) | STR · Burgers PDE, U+noise | coefficient error (%): failed -> 3.20%±2.198% | Improved |
| add low-rank regression on Ut (DLrSR vs rSTR) (ablation) | rSTR · Burgers PDE, {U,Ut}+noise | coefficient error (%): failed -> 3.084%±1.285% | Improved |
| add low-rank regression on Ut (DLrSR vs rSTR) (ablation) | rSTR · KS PDE, {U,Ut}+noise | coefficient error (%): failed -> 39.012%±2.715% | Mixed |
| add low-rank regression on Ut (DLrSR vs rSTR) (ablation) | rSTR · KdV PDE, {U,Ut}+noise | coefficient error (%): 9.840%±5.883% -> 9.203%±5.819% | Improved |
| add low-rank regression on Ut (DLrSR vs rSTR) (ablation) | rSTR · NLS PDE, {U,Ut}+noise | coefficient error (%): failed -> 0.356%±0.030% | Improved |
| DLrSR vs rSTR with U-only noise (ablation) | rSTR · KdV PDE, U+noise | coefficient error (%): 9.171%±5.595% -> 9.161%±5.583% | No clear effect |
Closest papers by meaning
- Efficient Learning of PDEs via Taylor Expansion and Sparse Decomposition into Value and Fourier Domains (AAAI 2024 · similarity 0.88)
- Learning Partial Differential Equations in Reproducing Kernel Hilbert Spaces (JMLR 2023 · similarity 0.87)
- Symmetry-Informed Governing Equation Discovery (NeurIPS 2024 · similarity 0.86)
- Mechanistic PDE Networks for Discovery of Governing Equations (ICML 2025 · similarity 0.86)
- CALM-PDE: Continuous and Adaptive Convolutions for Latent Space Modeling of Time-dependent PDEs (NeurIPS 2025 · similarity 0.85)
- LLM-SR: Scientific Equation Discovery via Programming with Large Language Models (ICLR 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.
