Research map / Learning theory and algorithms / Kernels and regression theory
On the Provable Generalization of Recurrent 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 |
|---|---|---|---|
| learn additive concept-class functions without the normalized input condition | Elman RNN (ReLU) with SGD · Additive concept class | population 0-1 error bound: previous works require ||X_l||≤ε; this work removes that condition | Helped |
| learn N-variable functions with nonlinear interactions across sequence positions | Elman RNN (ReLU) with SGD · N-variables concept class | learning complexity: when either N or l_0 is small, complexity is almost-polynomial in L | Helped |
Closest papers by meaning
- Understanding Generalization in Recurrent Neural Networks (ICLR 2020 · similarity 0.91)
- Can SGD Learn Recurrent Neural Networks with Provable Generalization? (NeurIPS 2019 · similarity 0.91)
- Learning and Generalization in RNNs (NeurIPS 2021 · similarity 0.90)
- Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes (NeurIPS 2024 · similarity 0.88)
- Generalization of Scaled Deep ResNets in the Mean-Field Regime (ICLR 2024 · similarity 0.87)
- Inverse Approximation Theory for Nonlinear Recurrent Neural Networks (ICLR 2024 · 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.