Research map / Learning theory and algorithms / Sample complexity
Learning Distributions Generated by One-Layer ReLU Networks
Shanshan Wu, Alexandros G Dimakis, Sujay Sanghavi
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 |
|---|---|---|---|
| Assume the bias vector is non-negative | Single-layer ReLU learning algorithm · Rectified Gaussian parameter estimation | sample complexity: \widetilde{O}(1/\epsilon^2) versus at least exponential in \norm{b}^2_{\infty} | Improved |
| Estimate row norms and pairwise angles separately | Single-layer ReLU learning algorithm · Rectified Gaussian parameter estimation | sample complexity: \widetilde{O}(1/\epsilon^2) | Improved |
| Increase the number of samples | Single-layer ReLU learning algorithm · Synthetic rectified Gaussian data (d=k=5, κ=1) | parameter estimation error and KL divergence | Improved |
| Increase the dimension | Single-layer ReLU learning algorithm · Synthetic rectified Gaussian data (n=5×10^5, κ=1) | KL divergence | Hurt |
| Increase the condition number | Single-layer ReLU learning algorithm · Synthetic rectified Gaussian data (n=5×10^5, d=5) | KL divergence | Hurt |
| Increase the number of samples | Two-layer ReLU learning algorithm · Two-layer ReLU generative model (d=10, p=k=5) | probability of success recovering A*: 0.30 -> 0.78 -> 0.99 (n=50, 100, 150) | Improved |
Closest papers by meaning
- Learning Distributions Generated by Single-Layer ReLU Networks in the Presence of Arbitrary Outliers (NeurIPS 2022 · similarity 0.91)
- Training Two-Layer ReLU Networks with Gradient Descent is Inconsistent (JMLR 2022 · similarity 0.87)
- Simplicity Bias and Optimization Threshold in Two-Layer ReLU Networks (ICML 2025 · similarity 0.87)
- Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes (NeurIPS 2024 · similarity 0.85)
- Compelling ReLU Networks to Exhibit Exponentially Many Linear Regions at Initialization and During Training (ICML 2025 · similarity 0.85)
- Noisy Interpolation Learning with Shallow Univariate ReLU Networks (ICLR 2024 · similarity 0.85)
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.
