Research map / Architectures and efficiency / CNN design
How to Characterize The Landscape of Overparameterized Convolutional Neural Networks
Yihong Gu, Weizhong Zhang, Cong Fang, Jason Lee, Tong Zhang
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 |
|---|---|---|---|
| graft layers of one network onto another with same initializer, different seed (ablation) | VGG-16 · CIFAR-10 | increased validation error | No clear effect |
| graft layers between nets with different initializers (he_uniform vs he_normal) (ablation) | VGG-16 · CIFAR-10 | increased validation error | Mixed |
| interpolate in feature-distribution space instead of weight space (ablation) | VGG-16 loss curve · CIFAR-10, 2 epochs | loss curve convexity | Improved |
Closest papers by meaning
- Optimization Landscape and Expressivity of Deep CNNs (ICML 2018 · similarity 0.87)
- Large Scale Structure of Neural Network Loss Landscapes (NeurIPS 2019 · similarity 0.87)
- Loss Landscape Characterization of Neural Networks without Over-Parametrization (NeurIPS 2024 · similarity 0.86)
- Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit (ICLR 2024 · similarity 0.85)
- Super Consistency of Neural Network Landscapes and Learning Rate Transfer (NeurIPS 2024 · similarity 0.85)
- Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks (ICML 2024 · similarity 0.84)
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.
