Research map / Optimization / Implicit bias and generalization
On Margin Maximization in Linear and ReLU Networks
Gal Vardi, Ohad Shamir, Nathan Srebro
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 fully-connected linear depth-2 network | KKT point of max-margin problem · Depth-2 linear | local/global optimality | Improved |
| Use depth-2 ReLU network (any listed structure except zero-input-free no-share) | KKT point of max-margin problem · Depth-2 ReLU | local/global optimality | Hurt |
| Add assumption of non-zero inputs to all neurons for ReLU no-share networks | KKT point of max-margin problem · Depth-2 ReLU N_no-share | local/global optimality | Mixed |
| Allow shared weights (convolutional) in linear depth-2 network | KKT point of max-margin problem · Depth-2 linear | local/global optimality | Hurt |
Closest papers by meaning
- Embedding Principle of Homogeneous Neural Network for Classification Problem (NeurIPS 2025 · similarity 0.89)
- Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks (ICLR 2025 · similarity 0.88)
- Achieving Margin Maximization Exponentially Fast via Progressive Norm Rescaling (ICML 2024 · similarity 0.87)
- Implicit Bias of Gradient Descent for Non-Homogeneous Deep Networks (ICML 2025 · similarity 0.87)
- Simplicity Bias and Optimization Threshold in Two-Layer ReLU Networks (ICML 2025 · similarity 0.87)
- Convex Relaxations of ReLU Neural Networks Approximate Global Optima in Polynomial Time (ICML 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.
