Research map / Optimization / Implicit bias and generalization
On the Convergence Rate of Training 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 |
|---|---|---|---|
| Use overparameterized width and train W with GD from random Gaussian initialization | Elman RNN with ReLU · RNN regression training sequences with δ-separable inputs | training loss: f (W^{(T)}) ≤ ε; T = Ω̃(poly(n, d, L)/δ² log 1/ε) | Helped |
| Use overparameterized width and train W with SGD from random Gaussian initialization | Elman RNN with ReLU · RNN regression training sequences with δ-separable inputs | training loss: f(W^{(T)}) ≤ ε; T = Ω̃(poly(n, d, L)/δ² log 1/ε) | Helped |
Closest papers by meaning
- Capacity and Trainability in Recurrent Neural Networks (ICLR 2017 · similarity 0.89)
- A Convergence Theory for Deep Learning via Over-Parameterization (ICML 2019 · similarity 0.89)
- State-Regularized Recurrent Neural Networks (ICML 2019 · similarity 0.89)
- On the Curse of Memory in Recurrent Neural Networks: Approximation and Optimization Analysis (ICLR 2021 · similarity 0.88)
- Recurrent neural networks: vanishing and exploding gradients are not the end of the story (NeurIPS 2024 · similarity 0.88)
- When Do Transformers Outperform Feedforward and Recurrent Networks? A Statistical Perspective (NeurIPS 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.