Research map / Probabilistic and scientific modeling / Differential equations and PDEs
KANO: Kolmogorov-Arnold Neural Operator
Jin Lee, Ziming Liu, Xinling Yu, Yixuan Wang, Haewon Jeong, Murphy Yuezhen Niu, Zheng Zhang
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 |
|---|---|---|---|
| replace KAN sub-networks with compact MLPs (ablation) | KANO · Synthetic operators G1-G3 (OOD Group B) | relative l2 loss: G1: 1.44 -> 6.59 | Mixed |
| replace KAN sub-networks with compact MLPs (ablation) | Q-KANO · Quantum DW (pos & mom) | state infidelity: 6.3 x 10^-6 -> 7.7 x 10^-6 | Mixed |
| use dual-domain pseudo-differential symbol instead of spectral-only kernels | KANO vs FNO · Synthetic operator G1 (Group B) | relative l2 loss: 98.8 -> 1.44 | Improved |
| add momentum PMF to position PMF supervision (ablation) | Q-KANO · Quantum NLSE | state infidelity: 6.1 x 10^-2 -> 5.6 x 10^-6 | Improved |
| train with position PMF only instead of full wave function (ablation) | Q-KANO · Quantum NLSE | state infidelity: 6.8 x 10^-6 -> 6.1 x 10^-2 | Hurt |
| freeze learned symbols and continue training (KANO_symbolic) (ablation) | KANO · Synthetic operators G1-G3 | relative l2 loss: G1 B: 1.44 -> 0.526 | Improved |
| use cubic instead of linear residual edge in activation KAN (ablation) | KANO · Synthetic operator G3 | loss and generalization | Improved |
| add localized enhancements (U-FNO, AM-FNO) to FNO | FNO · Synthetic operators (Group B) | relative l2 loss: G1: 98.8 -> 22.9; G2: 87.0 -> 339 | Mixed |
| use FNO with full-data training on long-horizon dynamics | FNO · Quantum Double-Well | state infidelity: 1.5 x 10^-2 vs 6.3 x 10^-6 for Q-KANO | Hurt |
Closest papers by meaning
- Neural Quantum Spectral Operator Learning for Solving Partial Differential Equations (NeurIPS 2026 · similarity 0.88)
- Deep-Koopman-KANDy: Dictionary Discovery for Deep-Koopman Operators with Kolmogorov-Arnold Networks for Dynamics (NeurIPS 2026 · similarity 0.87)
- Amortized Fourier Neural Operators (NeurIPS 2024 · similarity 0.87)
- Beyond Regular Grids: Fourier-Based Neural Operators on Arbitrary Domains (ICML 2024 · similarity 0.87)
- MgNO: Efficient Parameterization of Linear Operators via Multigrid (ICLR 2024 · similarity 0.86)
- Improved Operator Learning by Orthogonal Attention (ICML 2024 · 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.
