Research map / Learning theory and algorithms / Kernels and regression theory
Capacity Control of ReLU Neural Networks by Basis-Path Norm
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 basis-path regularization to SGD (ablation) | PlainNet34 · CIFAR-10 | test error rate (%): 6.34 -> 5.99 | Helped |
| Add basis-path regularization to Q-SGD (ablation) | PlainNet34 · CIFAR-10 | test error rate (%): 7.00 -> 5.73 | Helped |
| Add basis-path regularization to SGD (ablation) | ResNet34 · CIFAR-10 | test error rate (%): 5.71 -> 5.62 | Helped |
| Add basis-path regularization to Q-SGD (ablation) | ResNet34 · CIFAR-10 | test error rate (%): 6.66 -> 5.36 | Helped |
| Use a too-small regularization coefficient so its influence nearly disappears (ablation) | Basis-path regularization · CIFAR-10 image classification | test accuracy | No clear effect |
| Use a regularization coefficient greater than 1e-3 (ablation) | Basis-path regularization · CIFAR-10 image classification | training convergence: 1e-3 | Hurt |
Closest papers by meaning
- A path-norm toolkit for modern networks: consequences, promises and challenges (ICLR 2024 · similarity 0.89)
- Neural Characteristic Activation Analysis and Geometric Parameterization for ReLU Networks (NeurIPS 2024 · similarity 0.86)
- Compelling ReLU Networks to Exhibit Exponentially Many Linear Regions at Initialization and During Training (ICML 2025 · similarity 0.85)
- The Effect of Weight Precision on the Neuron Count in Deep ReLU Networks (ICML 2024 · similarity 0.85)
- Stable Minima of ReLU Neural Networks Suffer from the Curse of Dimensionality: The Neural Shattering Phenomenon (NeurIPS 2025 · similarity 0.84)
- Optimal Rates for Generalization of Gradient Descent for Deep ReLU Classification (NeurIPS 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.