cs.LGNov 1, 2026

Nonreciprocal Spherical Attention and Retrieval: Sharp Coarsening Clocks and Certified Score Correction

Authors: Faruk Alpay, Taylan Alpay

Organizations: Department of Computer Engineering, Bahçeşehir University, Istanbul, Türkiye · Department of Aerospace, University of Turkish Aeronautical Association, Ankara, Türkiye

Abstract

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⁡β→∞β−1log⁡Tβ=1−cos⁡φ\lim_{β\to\infty}β^{-1}\log T_β=1-\cosφ, 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(r2)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.

Figures & tables

Appendix figures & tables8 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Relevance-Guided Residual Calibration for Spectral Compression of Dense Retrieval Embeddings

    Oct 26, 2026Yongkang Li, Panagiotis Eustratiadis, Evangelos KanoulasEmbedding CompressionDense Retrieval

  2. Attention Calibration for Position-Fair Dense Retrieval

    Jun 1, 2026Andrianos Michail, Elias Schuhmacher, Juri Opitz +2Information RetrievalAttention Mechanisms

  3. Nearly Optimal Attention Coresets

    May 7, 2026Edo Liberty, Alexandr Andoni, Eldar KleinerSoftmax AttentionEfficient Attention