Research map / Optimization / Implicit bias and generalization
A Combinatorial Perspective on the Optimization of Shallow ReLU Networks
Michael S Matena, Colin Raffel
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 |
|---|---|---|---|
| replace gradient descent with greedy local search over zonotope vertices | shallow ReLU network · synthetic teacher-network data (MSE) | MSE | Improved |
| replace gradient descent with modified greedy local search (mGLS) | shallow ReLU network · MNIST 5/9 and Fashion MNIST coat/pullover binary classification | accuracy | Mixed |
| solve for a randomly chosen fixed activation pattern instead of batch gradient descent, with more hidden units | shallow ReLU network · synthetic data and Fashion MNIST coat/pullover | MSE and accuracy | Mixed |
Closest papers by meaning
- Optimization and Generalization of Gradient Descent for Shallow ReLU Networks with Minimal Width (JMLR 2026 · similarity 0.90)
- The Hidden Convex Optimization Landscape of Regularized Two-Layer ReLU Networks: an Exact Characterization of Optimal Solutions (ICLR 2022 · similarity 0.89)
- Activation-Descent Regularization for Input Optimization of ReLU Networks (ICML 2024 · similarity 0.88)
- Neural Characteristic Activation Analysis and Geometric Parameterization for ReLU Networks (NeurIPS 2024 · similarity 0.88)
- Compelling ReLU Networks to Exhibit Exponentially Many Linear Regions at Initialization and During Training (ICML 2025 · similarity 0.87)
- Simplicity Bias and Optimization Threshold in Two-Layer ReLU Networks (ICML 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.
