Metraipolis › archive › dc_3104cb85ba13
Single-Layer MeMo as a Randomized Hamming-Kernel Classifier — arXiv:2609.34562
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.34562
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T22:38:24.431Z
- SHA-256 of the archived text
aaba18c500010f2f9f8d152be6d39eb41e0a82de564d6dede5bc91363cc663fa- Stable URL of this page
https://metraipolis.com/documento/dc_3104cb85ba13
How to cite
Single-Layer MeMo as a Randomized Hamming-Kernel Classifier — arXiv:2609.34562 — arXiv (en), https://arxiv.org/abs/2609.34562 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3104cb85ba13 (Metraipolis archive dc_3104cb85ba13, sha256 aaba18c500010f2f9f8d152be6d39eb41e0a82de564d6dede5bc91363cc663fa)
BibTeX
@misc{dc3104cb85ba13,
title = {Single-Layer MeMo as a Randomized Hamming-Kernel Classifier — arXiv:2609.34562},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.34562},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3104cb85ba13; sha256 aaba18c500010f2f9f8d152be6d39eb41e0a82de564d6dede5bc91363cc663fa},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34562. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
MeMo (Zanzotto et al., 2025) is a recent language-model architecture that stores associations between token contexts and next tokens in a correlation matrix memory. In this work, we study its single-layer form and show that its ideal retrieval rule is a multiclass classifier based on the positional Hamming kernel. The MeMo architecture represents both the sequence features and the output labels with Gaussian random codes. Its score is therefore a doubly randomized sketch of the ideal classifier. Under independent input and output codebooks, we bound the errors introduced by context sketching and output decoding, characterize their dependence on model and data parameters, and give a margin-based guarantee for recovering the ideal prediction. Controlled simulations support the trends predicted by the analysis. On a restricted WikiText-2 next-token task, we compare single-layer MeMo with classical baselines and show that it can offer a useful trade-off among predictive accuracy, memory, and throughput, particularly on a GPU, where its matrix operations can be parallelized. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.34562 — 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 2026-10-07T22:14:28.229Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).