Metraipolis › archive › dc_115bf1551609
A Quantum Roadmap for Softmax Attention: Exact Born-Rule Analogs for Softmax Attention on the Probability Simplex — arXiv:2608.11173
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.11173
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T06:19:55.600Z
- SHA-256 of the archived text
1aef2060958de823cf9b19273e37f63da197d64f06d1aada2a549e59c965974c- Stable URL of this page
https://metraipolis.com/documento/dc_115bf1551609
How to cite
A Quantum Roadmap for Softmax Attention: Exact Born-Rule Analogs for Softmax Attention on the Probability Simplex — arXiv:2608.11173 — arXiv (en), https://arxiv.org/abs/2608.11173 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_115bf1551609 (Metraipolis archive dc_115bf1551609, sha256 1aef2060958de823cf9b19273e37f63da197d64f06d1aada2a549e59c965974c)
BibTeX
@misc{dc115bf1551609,
title = {A Quantum Roadmap for Softmax Attention: Exact Born-Rule Analogs for Softmax Attention on the Probability Simplex — arXiv:2608.11173},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.11173},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_115bf1551609; sha256 1aef2060958de823cf9b19273e37f63da197d64f06d1aada2a549e59c965974c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11173. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The attention mechanism forms the foundation of many modern AI models such as the Transformer. In one subclass of problems where attention is used, inputs and outputs are bound to the probability simplex so that all outputs sum to one. In this setting, softmax attention admits an exact, component-by-component quantum realization. Attention scores are Hadamard-test statistics on block-encoded projections of amplitude-encoded inputs. The exponential softmax is the interior of a cosine-squared family generated by Born-rule measurement under an exact bijection, whose boundary expresses sparse attention with exact zeros at finite parameter values. The softmax temperature is a repetition count where post-selected measurement rounds realize discretized inverse temperature exactly. Value aggregation is a deterministic column-loading channel that dilates the column-stochastic value matrix. The gated residual is the preparation angle of a single ancilla, with the additive identity at a mixing angle of $\pi$/2. Every learnable parameter is a rotation-gate angle. The composed layer is exact in the infinite-shot limit with one measure-and-reload step per attention score; a fully-coherent variant is $\epsilon$-approximate via quantum singular value transformation in the infinite depth limit. The algebraic core is machine-checked in Lean 4. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.LG). Categorie arXiv: Quantum Physics (quant-ph) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.11173 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T06:11:45.157Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).