Research map / Architectures and efficiency / CNN design
Implicit Convex Regularizers of CNN Architectures: Convex Optimization of Two- and Three-Layer Networks in Polynomial Time
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 |
|---|---|---|---|
| optimize the convex formulation instead of the conventional non-convex objective | two-layer CNN · CIFAR-10 full dataset, binary classification | training objective | Helped |
| optimize the convex formulation instead of the conventional non-convex objective | two-layer CNN · CIFAR-10 full dataset, binary classification | test accuracy | Helped |
| increase the number of filters | three-layer circular CNN trained with SGD · synthetic dataset (n=6, d=20) | convergence to the convex optimum | Helped |
| increase the number of filters | two-layer CNN trained with SGD · synthetic dataset (n=6, d=15) | convergence to the optimal objective | Helped |
Closest papers by meaning
- Neural Networks are Convex Regularizers: Exact Polynomial-time Convex Optimization Formulations for Two-layer Networks (ICML 2020 · similarity 0.93)
- Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions (ICML 2022 · similarity 0.92)
- Global Optimality Beyond Two Layers: Training Deep ReLU Networks via Convex Programs (ICML 2021 · similarity 0.92)
- Convex Relaxations of ReLU Neural Networks Approximate Global Optima in Polynomial Time (ICML 2024 · similarity 0.89)
- Convex Formulations for Training Two-Layer ReLU Neural Networks (ICLR 2025 · similarity 0.88)
- Exploring The Loss Landscape Of Regularized Neural Networks Via Convex Duality (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.