Metraipolis › archive › dc_97d6d0ceddc7
Derandomizing Dense Binary Hypervector Codebooks for Quantized Scalars — arXiv:2609.38471
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.38471
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T12:43:45.959Z
- SHA-256 of the archived text
00e5616c8a35ada7ed487a20ac8af679fef8f464b88ec4ba3211c9bd7d833ebc- Stable URL of this page
https://metraipolis.com/documento/dc_97d6d0ceddc7
How to cite
Derandomizing Dense Binary Hypervector Codebooks for Quantized Scalars — arXiv:2609.38471 — arXiv (en), https://arxiv.org/abs/2609.38471 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_97d6d0ceddc7 (Metraipolis archive dc_97d6d0ceddc7, sha256 00e5616c8a35ada7ed487a20ac8af679fef8f464b88ec4ba3211c9bd7d833ebc)
BibTeX
@misc{dc97d6d0ceddc7,
title = {Derandomizing Dense Binary Hypervector Codebooks for Quantized Scalars — arXiv:2609.38471},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.38471},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_97d6d0ceddc7; sha256 00e5616c8a35ada7ed487a20ac8af679fef8f464b88ec4ba3211c9bd7d833ebc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38471. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Hyperdimensional computing and vector symbolic architectures often represent quantized scalar levels by dense binary codebooks whose level-to-level similarity is intended to follow a prescribed function of scalar separation. At finite dimensionality, randomized scalar codebook constructions deviate from this target because of sampling noise, random-start imbalance, update-count fluctuations, component dependence, and finite-capacity effects. We develop a transition-based derandomization framework for dense binary scalar codebooks across two target-similarity families, with similarity decaying exponentially or linearly with level separation. The framework separates the target similarity law, the derandomization variant, and the concrete generator construction, making explicit how initialization, selection, update, and capacity-handling mechanisms shape the induced similarity profile. We formalize derandomization variants that separately constrain initial Hamming weight, update-count variability, and update balance, thereby controlling distinct sources of finite-dimensional error. For each family and variant, we derive the induced mean similarity, identify realization-wise and mean target-matching regimes, and derive exact finite-dimensional expressions for bias, variance, and root-mean-square error. Simulations across dimensions, quantization ranges, reference scalar levels, and generator constructions validate the theory and show how each constraint removes or reduces a specific source of similarity mismatch. The results provide practical guidance for choosing scalar codebook generators that more closely match a desired similarity law under finite-dimensional and hardware-relevant constraints. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI). Categorie arXiv: Information Theory (cs.IT) ; Artificial Intelligence (cs.AI); Neural and Evolutionary Computing (cs.NE). Pagina del lavoro: https://arxiv.org/abs/2609.38471 — 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 2026-10-07T12:14:13.883Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).