Research map / Optimization / Implicit bias and generalization
Implicit Bias of Gradient Descent on Linear Convolutional 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 full-width linear convolutional parameterization instead of a fully connected linear parameterization | Gradient descent on linear classifiers · Linearly separable binary classification | implicit bias | Mixed |
| Increase the depth of a full-width linear convolutional network | Linear convolutional networks · Linearly separable binary classification | frequency-domain sparsity penalty | Helped |
| Increase the depth of a fully connected linear network | Fully connected linear networks · Linearly separable binary classification | implicit bias | No clear effect |
Closest papers by meaning
- A unifying view on implicit bias in training linear neural networks (ICLR 2021 · similarity 0.90)
- Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy (NeurIPS 2020 · similarity 0.89)
- Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks (ICLR 2025 · similarity 0.89)
- A Convergence Analysis of Gradient Descent for Deep Linear Neural Networks (ICLR 2019 · similarity 0.88)
- Implicit Bias of Gradient Descent for Non-Homogeneous Deep Networks (ICML 2025 · similarity 0.88)
- Deep linear networks for regression are implicitly regularized towards flat minima (NeurIPS 2024 · similarity 0.88)
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.