Research map / Optimization / Implicit bias and generalization
An Unconstrained Layer-Peeled Perspective on Neural Collapse
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 |
|---|---|---|---|
| Train without explicit feature constraints or regularization using cross-entropy gradient flow | ULPM · ULPM | neural-collapse conditions at global minimizers | Helped |
| Use unconstrained training without weight decay | ResNet18 · MNIST and CIFAR-10 | neural-collapse metrics | Helped |
| Use cross-entropy gradient flow after the loss falls below log2 | ULPM · ULPM | loss | Helped |
| Use second-order tangent-space landscape analysis to exclude non-optimal directions | ULPM · ULPM | loss along fixed-norm directions | Helped |
| Rely on first-order KKT characterization alone | ULPM · ULPM | identification of neural-collapse solutions | Hurt |
Closest papers by meaning
- Neural Collapse under Gradient Flow on Shallow ReLU Networks for Orthogonally Separable Data (NeurIPS 2025 · similarity 0.90)
- Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse (ICLR 2025 · similarity 0.90)
- Neural Collapse Beyond the Unconstrained Features Model: Landscape, Dynamics, and Generalization in the Mean-Field Regime (ICML 2025 · similarity 0.89)
- Neural Collapse is Globally Optimal in Deep Regularized ResNets and Transformers (NeurIPS 2025 · similarity 0.88)
- The Persistence of Neural Collapse Despite Low-Rank Bias (NeurIPS 2025 · similarity 0.88)
- Neural Collapse in Cumulative Link Models for Ordinal Regression: An Analysis with Unconstrained Feature Model (NeurIPS 2025 · similarity 0.88)
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.