arXiv (All)
open access
Gaussian Equivalence for Multi-Head Self-Attention
A theoretical understanding of multi-head self-attention is fundamental to the study of modern neural networks. Using random matrix theory, we establish Gaussian equivalence for multi-head self-attention: replacing softmax attention with rescaled scores plus Gaussian noise preserves the limiting spe
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
- Softmax Attention on Gaussian Mixtures: Linear When It Can, Selective When It Must#1249078
- Optimal Discrimination of Gaussian States by Gaussian Measurements#1076832
- Algorithmic threshold for high-dimensional projection pursuit I: general theory#794206
- Algorithmic threshold for high-dimensional projection pursuit I: general theory#790187
- Learning with generalized negative dependence : probabilistic models of diversity for machine learning#284701
Record · ID 1234400
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