Research map / Optimization / Implicit bias and generalization
Porcupine Neural Networks: Approximating Neural Network Landscapes
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 |
|---|---|---|---|
| increase number of PNN hidden neurons k | Porcupine Neural Network · Synthetic two-layer network data (d=15, k*=20) | normalized MSE | Helped |
| increase ratio r/r* | Porcupine Neural Network · Spectral norm of psi[K]/psi[KL] when d = r | spectral norm (approximation error) | Helped |
| use PNN with k = 512, 1024, 2048 neurons to approximate a trained dense network with 512 neurons | Porcupine Neural Network · MNIST 1s vs 2s | normalized loss | Helped |
Closest papers by meaning
- The Hidden Convex Optimization Landscape of Regularized Two-Layer ReLU Networks: an Exact Characterization of Optimal Solutions (ICLR 2022 · similarity 0.86)
- No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths (ICML 2024 · similarity 0.86)
- Are Graph Neural Networks Optimal Approximation Algorithms? (NeurIPS 2024 · similarity 0.85)
- Simplicity Bias and Optimization Threshold in Two-Layer ReLU Networks (ICML 2025 · similarity 0.85)
- Near-optimal Sketchy Natural Gradients for Physics-Informed Neural Networks (ICML 2025 · similarity 0.85)
- Loss Landscape Characterization of Neural Networks without Over-Parametrization (NeurIPS 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.