Metraipolis › archive › dc_f73dda560f7a

Basin-Preserving Discretizations of Modern Hopfield Retrieval Dynamics: Energy Cells, Dissipation, and the Attention Limit — arXiv:2608.21304

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.21304
License (as archived)
CC0-1.0
Archived
2026-10-18T10:44:17.540Z
SHA-256 of the archived text
1d410c0a202e20deb3bf72ec9661a943ab4b276dfd2b7879f7a0956705ad880d
Stable URL of this page
https://metraipolis.com/documento/dc_f73dda560f7a

How to cite

Basin-Preserving Discretizations of Modern Hopfield Retrieval Dynamics: Energy Cells, Dissipation, and the Attention Limit — arXiv:2608.21304 — arXiv (en), https://arxiv.org/abs/2608.21304 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f73dda560f7a (Metraipolis archive dc_f73dda560f7a, sha256 1d410c0a202e20deb3bf72ec9661a943ab4b276dfd2b7879f7a0956705ad880d)
BibTeX
@misc{dcf73dda560f7a,
  title = {Basin-Preserving Discretizations of Modern Hopfield Retrieval Dynamics: Energy Cells, Dissipation, and the Attention Limit — arXiv:2608.21304},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.21304},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f73dda560f7a; sha256 1d410c0a202e20deb3bf72ec9661a943ab4b276dfd2b7879f7a0956705ad880d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.21304. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The retrieval dynamics of a modern Hopfield network is the gradient flow of a log-sum-exp energy, while the attention update is its exact difference-of-convex minimization step. We study which time discretizations preserve not only energy decay and equilibria but also basins of attraction. We introduce energy cells, connected components of sublevel sets containing one attractor and no other critical point. Our main theorem shows that every finite energy cell below the escape energy is contained simultaneously in the basin of the continuous flow, every relaxed attention map $\Psi_\theta=(1-\theta)\,\mathrm{id}+\theta\,\mathrm{attention}$ for $0<\theta<2$, and implicit Euler throughout its uniqueness regime. A parameter-uniform unit-curvature majorant yields unconditional dissipation and a monotone interpolation of each discrete step. We also derive explicit local contraction bounds near well-separated patterns, with a certified optimal slight overrelaxation; characterize proximal tunneling and overshoot beyond the preservation regimes; compare first-order error constants; establish an order barrier for scalar reparametrizations of the relaxed family; construct a second-order scalar-auxiliary-variable scheme; and extend cell preservation to damped difference-of-convex iterations in Bregman geometry, including a certified overrelaxed window under bounded asymmetry. Nine numerical campaigns test the bounds and failure mechanisms. In two-dimensional basin experiments, all observed disagreements between continuous and discrete retrieval occur above the attractor-specific numerically inferred escape level.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-08-24 in math.NA).
Categorie arXiv: Numerical Analysis (math.NA) ; Neural and Evolutionary Computing (cs.NE).
Pagina del lavoro: https://arxiv.org/abs/2608.21304 — 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 2026-10-18T10:38:56.454Z dalla pagina https://arxiv.org/catchup/math.NA/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).