arXiv (All)
open access
A Fix for Softmax and Cross-Entropy
Standard implementations of softmax, log-softmax, and cross-entropy have two numerical bugs. The first bug, Softmax Collapse, rounds the target logit's gradient to zero if that one logit is much larger than the others, resulting in gradients that no longer sum to zero. The second bug, Softmax Cancel
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- A Fix for Softmax and Cross-Entropy#1417819
- From Parallel to Sequential: Small-Batch Noise Restores Simplicity Bias of Muon#1341750
- Softpick: No Attention Sink, No Massive Activations with Rectified Softmax#149268
- Exploring deep neural networks via layer-peeled model: Minority collapse in imbalanced training#336796
- Layerwise Decoupling for Stable Structured Sparsification of Fully Connected Layers#1035095
Record · ID 1424775
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive