Research map / Optimization / Implicit bias and generalization
Gradient Descent Maximizes the Margin of Homogeneous 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 a loss-based learning rate scheduler instead of a constant learning rate of 0.01 | CNN trained with SGD · MNIST | normalized margin increase after 10000 epochs: ≈ 1.8 × 10^{-4} -> ≈ 1.2 × 10^{-3} | Helped |
| Use a loss-based learning rate scheduler instead of a constant learning rate of 0.01 | CNN trained with SGD · MNIST | training loss: < 10^{-800} after 9000 epochs | Helped |
| Train for longer after the model is fitted | CNN · MNIST and CIFAR-10 | L^2-robustness | Helped |
Closest papers by meaning
- The Asymmetric Maximum Margin Bias of Quasi-Homogeneous Neural Networks (ICLR 2023 · similarity 0.93)
- Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization (NeurIPS 2024 · similarity 0.91)
- Implicit Bias of Gradient Descent for Non-Homogeneous Deep Networks (ICML 2025 · similarity 0.90)
- Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks (ICLR 2025 · similarity 0.90)
- Achieving Margin Maximization Exponentially Fast via Progressive Norm Rescaling (ICML 2024 · similarity 0.90)
- Gradient Descent Converges Arbitrarily Fast for Logistic Regression via Large and Adaptive Stepsizes (ICML 2025 · similarity 0.89)
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.