Research map / Architectures and efficiency / RNNs and normalization
A Geometric Analysis of Neural Collapse with Unconstrained Features
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 |
|---|---|---|---|
| apply weight decay on last-layer features H rather than all network weights (ablation) | ResNet18 · MNIST | test accuracy: 99.60 -> 99.57 | No clear effect |
| apply weight decay on last-layer features H rather than all network weights (ablation) | ResNet18 · CIFAR10 | test accuracy: 78.42 -> 77.92 | No clear effect |
| fix last-layer classifier as a Simplex ETF (ablation) | ResNet18/ResNet50 · MNIST, CIFAR10 | test accuracy | No clear effect |
| set feature dimension d=K instead of large d (ablation) | ResNet18/ResNet50 · MNIST, CIFAR10 | test accuracy | No clear effect |
| set feature dimension d=K instead of large d (ablation) | ResNet18 · CIFAR10 | parameter/memory cost: -20.70% | Helped |
| use different optimizers (SGD, Adam, LBFGS) | ResNet18 · CIFAR10 | test accuracy | Mixed |
Closest papers by meaning
- Guiding Neural Collapse: Optimising Towards the Nearest Simplex Equiangular Tight Frame (NeurIPS 2024 · similarity 0.93)
- Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse (ICLR 2025 · similarity 0.92)
- Neural Collapse Beyond the Unconstrained Features Model: Landscape, Dynamics, and Generalization in the Mean-Field Regime (ICML 2025 · similarity 0.92)
- Neural Collapse under Gradient Flow on Shallow ReLU Networks for Orthogonally Separable Data (NeurIPS 2025 · similarity 0.91)
- Neural Collapse in Cumulative Link Models for Ordinal Regression: An Analysis with Unconstrained Feature Model (NeurIPS 2025 · similarity 0.91)
- Generalized Neural Collapse for a Large Number of Classes (ICML 2024 · similarity 0.90)
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.