Metraipolis › archive › dc_e390abddeab4
Nonreciprocal Spherical Attention and Retrieval: Sharp Coarsening Clocks and Certified Score Correction — arXiv:2611.02237
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02237
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T11:21:26.718Z
- SHA-256 of the archived text
66a870844e84682005d06305ff9b4b0ae8f2b781f7d466a6457a9f1f944b91d9- Stable URL of this page
https://metraipolis.com/documento/dc_e390abddeab4
How to cite
Nonreciprocal Spherical Attention and Retrieval: Sharp Coarsening Clocks and Certified Score Correction — arXiv:2611.02237 — arXiv (en), https://arxiv.org/abs/2611.02237 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e390abddeab4 (Metraipolis archive dc_e390abddeab4, sha256 66a870844e84682005d06305ff9b4b0ae8f2b781f7d466a6457a9f1f944b91d9)
BibTeX
@misc{dce390abddeab4,
title = {Nonreciprocal Spherical Attention and Retrieval: Sharp Coarsening Clocks and Certified Score Correction — arXiv:2611.02237},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02237},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e390abddeab4; sha256 66a870844e84682005d06305ff9b4b0ae8f2b781f7d466a6457a9f1f944b91d9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02237. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We develop nonreciprocal spherical attention as a mathematical framework for coarsening and compressed nearest-neighbor retrieval. For two shrinking acute blocks whose centers have zero skew pairing and whose total mass ratio is subexponential in inverse temperature, we prove $\lim_{\beta\to\infty}\beta^{-1}\log T_\beta=1-\cos\phi$, without restricting particle-count growth. An explicit three-body flow has two rigorously separated metastable exponents. For finite compression, mass centering yields a sharp $O(r^2)$ attention-output error bound at fixed temperature, with an explicit spherical-normalization correction. We formulate skew query-side score calibration as a strictly convex moment problem and derive a unique normal equation, residual-based optimization certificates, and bounded low-rank projections. A norm-aware margin objective calibrates native squared-distance rankings. Experiments use semantic retrieval data, one million visual descriptors with three codebook seeds, and a ten-million-vector FAISS IVF-PQ index with recomputed exact cosine ground truth. On SIFT1M, skew margin calibration raises native-L2 hit@10 from 0.8926 to 0.8948; symmetric calibration reaches 0.8996. The ten-million-vector index reaches 0.8827 hit@10 at 0.1794 ms per query in a four-thread batch benchmark, while validation selects no skew update. Exact streamed attention over ten million keys evaluates compressed memory on 1,024 held-out queries. Independent matrix solves, automatic differentiation, finite differences, interval arithmetic, full-flow tests, and nine Rocq-checked algebra lemmas support reproducibility. Directionality alone does not establish retrieval superiority.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Information Retrieval (cs.IR); Dynamical Systems (math.DS).
Pagina del lavoro: https://arxiv.org/abs/2611.02237 — 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 2026-11-03T11:02:37.594Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).