Research map / Optimization / Implicit bias and generalization
Understanding the Generalization of Adam in Learning Neural Networks with Proper Regularization
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 Adam instead of SGD | Two-layer CNN · Synthetic data, test set | test error: 0 -> 0.884 | Hurt |
| Use Adam instead of gradient descent | Two-layer CNN with weight decay · Nonconvex synthetic data | test error: o(1) -> ≥ 1/2-o(1) | Hurt |
| Use Adam instead of gradient descent | Convex model with positive weight decay · Convex setting | test error difference: ± o(1) | No clear effect |
Closest papers by meaning
- Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks (NeurIPS 2025 · similarity 0.93)
- A Comprehensive Framework for Analyzing the Convergence of Adam: Bridging the Gap with SGD (ICML 2025 · similarity 0.90)
- The Rich and the Simple: On the Implicit Bias of Adam and SGD (NeurIPS 2025 · similarity 0.89)
- Why Do We Need Weight Decay in Modern Deep Learning? (NeurIPS 2024 · similarity 0.88)
- Do Neural Networks Need Gradient Descent to Generalize? A Theoretical Study (NeurIPS 2025 · similarity 0.87)
- On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent (ICLR 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.