Research map / Probabilistic and scientific modeling / Differential equations and PDEs
Discovering Scaling Exponents with Physics-Informed Müntz-Szász Networks
Gnankan Landry Regis N'guessan, Bum Jun Kim
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 constraint loss sin^2(mu*omega) weighted by coefficient magnitude (ablation) | MSN-PINN · Corner singularity (Laplace, 270 degree wedge) | relative exponent error (%): 14.6% -> 0.009% | Improved |
| use MSN-PINN instead of standard tanh PINN with post-hoc power-law fitting | wedge problem · Wedge (vs standard PINN) | exponent error: 0.278 -> 0.013 | Improved |
| use MSN-PINN instead of standard PINN with post-hoc fitting | singular forcing problem · Singular forcing | exponent error | Improved |
| learn exponents with MSN-PINN from physics only (no labels) | singular ODE · Singular ODE (physics only) | relative exponent error (%): 0.5000 -> 0.4934 | Improved |
| use redundant exponent terms (K = 4) for singular forcing | MSN-PINN · Singular forcing | exponent recovery | Improved |
| use two-timescale optimization (slower exponent learning rate) | MSN-PINN · all settings | stability | No clear effect |
Closest papers by meaning
- Analyzing Neural Scaling Laws in Two-Layer Networks with Power-Law Data Spectra (ICLR 2025 · similarity 0.86)
- Emergence and scaling laws in SGD learning of shallow neural networks (NeurIPS 2025 · similarity 0.85)
- Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks (ICML 2025 · similarity 0.85)
- Number Theoretic Accelerated Learning of Physics-Informed Neural Networks (AAAI 2025 · similarity 0.84)
- Per-Loss Adapters for Gradient Conflict in Physics-Informed Neural Networks (NeurIPS 2026 · similarity 0.84)
- Learning from Integral Losses in Physics Informed Neural Networks (ICML 2024 · similarity 0.84)
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.
