Metraipolis › archive › dc_2bde6e6ffedb
ALPHABET: A Laplace-Pole History Aggregator with Banked Exponential Transport — arXiv:2608.24051
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.24051
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T06:35:54.297Z
- SHA-256 of the archived text
520f0f9d5103952ec941650bec0b7dc01e492d4f3ff4066890662aca8c138ee5- Stable URL of this page
https://metraipolis.com/documento/dc_2bde6e6ffedb
How to cite
ALPHABET: A Laplace-Pole History Aggregator with Banked Exponential Transport — arXiv:2608.24051 — arXiv (en), https://arxiv.org/abs/2608.24051 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2bde6e6ffedb (Metraipolis archive dc_2bde6e6ffedb, sha256 520f0f9d5103952ec941650bec0b7dc01e492d4f3ff4066890662aca8c138ee5)
BibTeX
@misc{dc2bde6e6ffedb,
title = {ALPHABET: A Laplace-Pole History Aggregator with Banked Exponential Transport — arXiv:2608.24051},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.24051},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2bde6e6ffedb; sha256 520f0f9d5103952ec941650bec0b7dc01e492d4f3ff4066890662aca8c138ee5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.24051. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Can a sequence model remain competitive with only a few thousand parameters and an explicitly auditable prediction interface? We introduce ALPHABET, a compact linear-time model that compresses temporal history into stable complex pole modes: a direct bank synthesizes its modal states back into the feature trajectory, an independent cascaded bank analyzes the transformed trajectory without resynthesis, and an affine head reads only modal energies and lag moments from both banks. We characterize the temporal information this descriptor retains: for a stationary, fully observed feature process, each mode energy is a frequency-localized measurement of the second-order spectrum, the continuum of such measurements identifies the spectrum, and almost every mode separates any fixed finite set of spectrally distinct classes. On a Gaussian control with matched low-lag statistics, the learned descriptor approaches the Bayes oracle where raw autocovariances remain at chance. Across the fixed 82-task registry, ALPHABET attains mean rank 3.97 in the complete ten-family comparison. At the common-width D=64 runtime anchor, its 6,437 parameters deliver 5.02 times faster inference and 3.93 times faster complete training steps than the nine baselines on average. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-26 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.24051 — 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 2026-10-18T06:28:52.214Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-26?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).