Research map / Learning theory and algorithms / Sample complexity
On the Complexity of Learning 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 sharpness times the square root of input dimension | SGD training of one-hidden-layer networks on s-wave functions · Gaussian, coordinate-wise exp(-|x_i|), and uniform l1-ball inputs | test error | Hurt |
Closest papers by meaning
- Sharper Guarantees for Learning Neural Network Classifiers with Gradient Methods (ICLR 2025 · similarity 0.91)
- On the Complexity of Learning Sparse Functions with Statistical and Gradient Queries (NeurIPS 2024 · similarity 0.90)
- New Complexity-Theoretic Frontiers of Tractability for Neural Network Training (NeurIPS 2023 · similarity 0.90)
- Can Neural Networks Achieve Optimal Computational-statistical Tradeoff? An Analysis on Single-Index Model (ICLR 2025 · similarity 0.88)
- Sample complexity of data-driven tuning of model hyperparameters in neural networks with structured parameter-dependent dual function (NeurIPS 2025 · similarity 0.88)
- On the Hardness of Training Deep Neural Networks Discretely (AAAI 2025 · similarity 0.87)
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.