Research map / Architectures and efficiency / RNNs and normalization
ResNet with one-neuron hidden layers is a Universal Approximator
Hongzhou Lin, Stefanie Jegelka
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 one-neuron residual blocks instead of fully connected layers of width d | Unit ball classification · Unit ball classification | decision-boundary approximation quality | Improved |
| Increase depth | One-neuron ResNet · Unit ball classification | decision-boundary approximation quality | Improved |
| Increase depth | Fully connected network with width d · Unit ball classification | decision-boundary approximation quality | No clear effect |
Closest papers by meaning
- Characterizing ResNet's Universal Approximation Capability (ICML 2024 · similarity 0.91)
- Understanding Deep Neural Networks with Rectified Linear Units (ICLR 2018 · similarity 0.89)
- Compelling ReLU Networks to Exhibit Exponentially Many Linear Regions at Initialization and During Training (ICML 2025 · similarity 0.87)
- ReLU Network with Width $d+\mathcal{O}(1)$ Can Achieve Optimal Approximation Rate (ICML 2024 · similarity 0.87)
- Most ReLU Networks Admit Identifiable Parameters (NeurIPS 2026 · similarity 0.86)
- Approximation theory for 1-Lipschitz ResNets (NeurIPS 2025 · 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.
