Research map / Optimization / Implicit bias and generalization
Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data
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 |
|---|---|---|---|
| Use SGD with sufficient overparameterization and random initialization | Two-layer ReLU network on well-separated mixture data · Well-separated mixture distributions | test error: at most ε | Helped |
| Increase the number of hidden units (ablation) | SGD on two-layer ReLU network · Synthetic data | test accuracy | Helped |
| Increase the number of hidden units (ablation) | SGD on two-layer ReLU network · MNIST | test accuracy | Mixed |
Closest papers by meaning
- SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data (ICLR 2018 · similarity 0.90)
- An Improved Analysis of Training Over-parameterized Deep Neural Networks (NeurIPS 2019 · similarity 0.89)
- Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks (ICML 2019 · similarity 0.89)
- Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks (ICML 2024 · similarity 0.87)
- Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data (ICLR 2024 · similarity 0.87)
- Simplicity Bias and Optimization Threshold in Two-Layer ReLU Networks (ICML 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.