Metraipolis › archive › dc_423210f044a5

Intrinsic Associative Memory on Riemannian Manifolds: Curvature, Capacity, and Emergent Modes — arXiv:2609.35948

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35948
License (as archived)
CC0-1.0
Archived
2026-10-07T16:25:04.573Z
SHA-256 of the archived text
769e356e585ec48df50ee95abc8bca6d0af531302734d2b8c865207d168db472
Stable URL of this page
https://metraipolis.com/documento/dc_423210f044a5

How to cite

Intrinsic Associative Memory on Riemannian Manifolds: Curvature, Capacity, and Emergent Modes — arXiv:2609.35948 — arXiv (en), https://arxiv.org/abs/2609.35948 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_423210f044a5 (Metraipolis archive dc_423210f044a5, sha256 769e356e585ec48df50ee95abc8bca6d0af531302734d2b8c865207d168db472)
BibTeX
@misc{dc423210f044a5,
  title = {Intrinsic Associative Memory on Riemannian Manifolds: Curvature, Capacity, and Emergent Modes — arXiv:2609.35948},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35948},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_423210f044a5; sha256 769e356e585ec48df50ee95abc8bca6d0af531302734d2b8c865207d168db472},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35948. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Geometry does more than constrain an associative memory: curvature determines what it remembers and which states it creates. We develop intrinsic dense associative memories on Riemannian manifolds by casting memory as Epanechnikov kernel-density mode seeking. We compare geodesic and volume-corrected energies and show that curvature separates their behavior. We prove that geodesic memory always retains an isolated pattern, while corrected memory obeys a sharp Ricci-curvature threshold: positive curvature can erase memories in high dimensions, while negative curvature reinforces them. We derive geodesic capacity scalings of $q_\beta^{-1/2}$ for retaining every pattern and $q_\beta^{-1}$ for a typical one, where $q_\beta$ is the pairwise kernel-overlap probability. We show how overlap \emph{creates} novel memories: designed $N$-pattern configurations realize all $2^N-1$ subset modes, but random data at the storage threshold yield only a Poisson number. We establish exact one-step recall using Riemannian mean shift. In simulations, we recover the predicted curvature transition and every designed mode. On WordNet's full noun hierarchy, we demonstrate that volume correction improves low-capacity retrieval. Together, our work shows that curvature is a design variable for associative memory, not merely a property of the data.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2609.35948 — 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 2026-10-07T15:54:53.748Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).