Research map / Learning theory and algorithms / Sample complexity
Learning single-index models with shallow 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 |
|---|---|---|---|
| add ridge fine-tuning of the output layer after gradient-flow direction recovery | shallow ReLU network with frozen biases · synthetic single-index model | excess risk rate | Helped |
| increase information exponent s from 1-2 to 3 | shallow ReLU network with frozen biases · synthetic piecewise linear link, d=50 | samples needed for direction recovery | Hurt |
| increase input dimension d | shallow ReLU network with frozen biases · synthetic single-index model | samples for full recovery |m|->1 | Hurt |
Closest papers by meaning
- Can Neural Networks Achieve Optimal Computational-statistical Tradeoff? An Analysis on Single-Index Model (ICLR 2025 · similarity 0.88)
- Symmetric Single Index Learning (ICLR 2024 · similarity 0.88)
- Shallow diffusion networks provably learn hidden low-dimensional structure (ICLR 2025 · similarity 0.87)
- Implicit Bias of Mirror Flow for Shallow Neural Networks in Univariate Regression (ICLR 2025 · similarity 0.87)
- Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit (NeurIPS 2024 · similarity 0.86)
- Deep linear networks for regression are implicitly regularized towards flat minima (NeurIPS 2024 · 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.