No article text was recorded for this version.
softmax saturation
Version 1 of 112 papers20 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Graph Neural Network Generalization With Gaussian Mixture Model Based Augmentation
- Blog: Cross-entropy vs. squared error training: a theoretical and experimental comparison
- Blog: Universal One-third Time Scaling in Learning Peaked Distributions
- Blog: Noisy Softmax: Improving the Generalization Ability of DCNN via Postponing the Early Softmax Saturation
- Blog: Gaussian Mixture Models Based Augmentation Enhances GNN Generalization
- Blog: NormFace: L2 Hypersphere Embedding for Face Verification
- Blog: Class-Variant Margin Normalized Softmax Loss for Deep Face Recognition
- Blog: Decoupled Entropy Minimization
- Blog: Parametric ρ-Norm Scaling Calibration
- Blog: Feature Contraction: New ConvNet Regularization in Image Classification
- Blog: Different Layers, Different Manifolds: Module-Wise Weight-Space Geometry in Transformer Optimization
- Blog: Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_softmax_saturation_2ee45bca,
title = {softmax saturation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/softmax-saturation/rdr_2ee45bcaad26493594273cde373a4ee6},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_softmax_saturation_2ee45bca_v1,
title = {softmax saturation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/softmax-saturation/rdr_2ee45bcaad26493594273cde373a4ee6/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}