Research map / Architectures and efficiency / RNNs and normalization
Spurious Local Minima are Common in Two-Layer ReLU Neural Networks
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 network width from n=k to n=k+1 (ablation) | Two-layer ReLU network trained by gradient descent · Gaussian population squared loss, k=8 through k=19 | runs converging to spurious local minima: 12.6% -> 0.1% (k=8); 93.4% -> 49.1% (k=19) | Helped |
| Increase target/network size while keeping n=k | Two-layer ReLU network trained by gradient descent · Gaussian population squared loss, k=6 through k=20 | runs converging to spurious local minima: 0.3% -> 94% | Hurt |
| Use n≥k+2 neurons (ablation) | Two-layer ReLU network trained by gradient descent · Gaussian population squared loss, tested with n≤20 | encountered spurious local minima | Helped |
Closest papers by meaning
- Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes (NeurIPS 2024 · similarity 0.90)
- Stable Minima of ReLU Neural Networks Suffer from the Curse of Dimensionality: The Neural Shattering Phenomenon (NeurIPS 2025 · similarity 0.89)
- Convex Relaxations of ReLU Neural Networks Approximate Global Optima in Polynomial Time (ICML 2024 · similarity 0.89)
- Universal Consistency of Wide and Deep ReLU Neural Networks and Minimax Optimal Convergence Rates for Kolmogorov-Donoho Optimal Function Classes (ICML 2024 · similarity 0.89)
- Simplicity Bias and Optimization Threshold in Two-Layer ReLU Networks (ICML 2025 · similarity 0.89)
- Global Minimizers of $\ell^p$-Regularized Objectives Yield the Sparsest ReLU Neural Networks (NeurIPS 2025 · similarity 0.89)
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.