Research map / Learning theory and algorithms / Prediction and decision losses
Are All Losses Created Equal: A Neural Collapse Perspective
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 |
|---|---|---|---|
| Use MSE instead of CE | WideResNet18-2 · miniImageNet, 800 epochs | test accuracy: 0.7930 -> 0.7962 | No clear effect |
| Use FL instead of CE | WideResNet18-2 · miniImageNet, 800 epochs | test accuracy: 0.7930 -> 0.7932 | No clear effect |
| Use LS instead of CE | WideResNet18-2 · miniImageNet, 800 epochs | test accuracy: 0.7930 -> 0.8020 | No clear effect |
| Use different losses rather than CE | WideResNet18-0.25 · miniImageNet, 100 epochs | test accuracy: 0.7195, 0.6915, 0.7020 and 0.7040 | Mixed |
Closest papers by meaning
- Neural Collapse is Globally Optimal in Deep Regularized ResNets and Transformers (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 0.90)
- The Persistence of Neural Collapse Despite Low-Rank Bias (NeurIPS 2025 · similarity 0.90)
- Neural Collapse under Gradient Flow on Shallow ReLU Networks for Orthogonally Separable Data (NeurIPS 2025 · similarity 0.89)
- Neural collapse vs. low-rank bias: Is deep neural collapse really optimal? (NeurIPS 2024 · similarity 0.89)
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.