Research map / Learning theory and algorithms / Kernels and regression theory
CauchyNet: Compact and Data-Efficient Learning using Holomorphic Activation Functions
Hong-Kun Zhang, Xin Li, Sikun Yang, Zhihong Jeff Xia
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 Cauchy inversion activation instead of ReLU in a 128-unit single-hidden-layer network | CauchyNet · 1D rational-spike regression | MSE / peak fit | Improved |
| CauchyNet versus SIREN, N-BEATS, FNN | CauchyNet · Sharp-peak function approximation | MAE: 3.2 -> 1.5 | Improved |
| CauchyNet versus baselines for forecasting | CauchyNet · M4 subset trend forecasting | MAE: 10+ -> 2.3 | Improved |
| CauchyNet versus baselines for gap filling | CauchyNet · 1D gap-filling imputation | MSE and MAE | Improved |
| add imaginary-part penalty to loss (ablation) | CauchyNet · 1D sharp-peak function | test MSE | Improved |
| vary imaginary penalty lambda over 0.1 to 1.5 (ablation) | CauchyNet · 1D sharp-peak function | test MSE | Mixed |
| increase hidden size (ablation) | CauchyNet · Parameter sensitivity heatmaps | test MSE | Improved |
| use learning rate 0.01 with weight decay 1e-5 (ablation) | CauchyNet · Parameter sensitivity heatmaps | test MSE | Improved |
Closest papers by meaning
- Reproducing Kernel Banach Space Models for Neural Networks with Application to Rademacher Complexity Analysis (NeurIPS 2025 · similarity 0.86)
- Sharp Generalization for Nonparametric Regression by Over-Parameterized Neural Networks: A Distribution-Free Analysis in Spherical Covariate (ICML 2025 · similarity 0.85)
- Cauchy-Schwarz Regularizers (ICLR 2025 · similarity 0.84)
- The Nuclear Route: Sharp Asymptotics of ERM in Overparameterized Quadratic Networks (NeurIPS 2025 · similarity 0.84)
- Generalization in Kernel Regression Under Realistic Assumptions (ICML 2024 · similarity 0.84)
- Generalization Bounds and Model Complexity for Kolmogorov–Arnold Networks (ICLR 2025 · 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.
