Metraipolis › archive › dc_f53fa9ba4eda

Dynamical mean-field theory for associative memory with block-correlated patterns — arXiv:2610.40060

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.40060
License (as archived)
CC0-1.0
Archived
2026-11-01T02:53:13.643Z
SHA-256 of the archived text
df5fb41b3d605240ca7790ca952d5bc37bb1d92aa8766c1771a93d194f2959fd
Stable URL of this page
https://metraipolis.com/documento/dc_f53fa9ba4eda

How to cite

Dynamical mean-field theory for associative memory with block-correlated patterns — arXiv:2610.40060 — arXiv (en), https://arxiv.org/abs/2610.40060 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f53fa9ba4eda (Metraipolis archive dc_f53fa9ba4eda, sha256 df5fb41b3d605240ca7790ca952d5bc37bb1d92aa8766c1771a93d194f2959fd)
BibTeX
@misc{dcf53fa9ba4eda,
  title = {Dynamical mean-field theory for associative memory with block-correlated patterns — arXiv:2610.40060},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40060},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f53fa9ba4eda; sha256 df5fb41b3d605240ca7790ca952d5bc37bb1d92aa8766c1771a93d194f2959fd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40060. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In associative memories storing correlated patterns, retrieval of individual memories can compete with symmetric mixed states. A dynamical description is needed to determine how the initial state selects between these outcomes. We extend the generating-functional dynamical mean-field theory (DMFT) for independent patterns to independent blocks of correlated binary patterns of fixed finite size. The resulting effective single-neuron process has a self-consistent cross-talk noise covariance and self-feedback coefficients that depend on the block-covariance eigenvalues. For hierarchically correlated patterns with nonmonotonic transfer, increasing the loading can permit retrieval from an imperfect initial state before further loading prevents it. DMFT reproduces the retrieval trajectories and basin geometry found in direct simulations. Near the lower boundary of this re-entrant region, direct networks reveal stationary saddles separating coexisting mixed and target-retrieval states. Parameter sensitivities of DMFT trajectories predict nearby shifts of this boundary. At the tested upper boundary, retrieval remains accessible from initial states with larger target overlap, indicating a change in basin access. Under fixed-point convergence assumptions, the theory recovers the equations of generalized self-consistent signal-to-noise analysis.

Tema degli esploratori: fisica e astronomia (elenco arXiv cond-mat.dis-nn, nuovi lavori del giorno).
Categorie arXiv: Disordered Systems and Neural Networks (cond-mat.dis-nn).
Pagina del lavoro: https://arxiv.org/abs/2610.40060 — 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 2026-11-01T02:20:13.241Z dalla pagina https://arxiv.org/list/cond-mat.dis-nn/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).