arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.03115cond-mat.stat-mech
收藏

通过动力学平均场理论测试高阶Hopfield模型中对角相互作用的作用

Testing the Role of Diagonal Interactions in High-Order Hopfield Models via Dynamical Mean-Field Theory

The University of Tokyo(东京大学)

Yuto Sumikawa, Yoshiyuki Kabashima

AI总结:

研究高阶Hopfield模型中对角相互作用对动态检索特性的影响,发现即使在无对角相互作用的模型中,慢动态和吸引盆地扩大仍存在,表明高阶相互作用的内在性质是主要原因。

摘要:

高阶Hopfield模型的扩展在平衡状态下表现出显著增强的存储容量,但其动态检索特性仍不明确。本文通过动力学平均场理论分析Krotov-Hopfield型密集联想记忆,发现成功与失败检索之间的转变伴随显著的慢动态。因此,数值模拟中观察到的有效吸引盆地远超平衡统计力学的预测。假设这种差异源于Krotov-Hopfield模型中的对角(自相互作用)贡献,它们产生大量低阶相互作用项,可能在检索边界附近诱导玻璃态弛豫。为检验这一假设,我们分析了另一种高阶联想记忆模型,即Abbott-Arian型p-体Hopfield模型,其中此类对角贡献被构造排除。通过动力学平均场理论,我们推导出有效的单站点过程及支配检索动态的闭合宏观方程。研究发现,即使在该模型中,慢动态和显著的吸引盆地扩大仍存在。这些结果表明,检索边界附近动态减慢不能主要归因于对角自相互作用效应,而是源于高阶相互作用的内在性质。

英文摘要:

High-order extensions of the Hopfield model are known to exhibit dramatically enhanced storage capacity at equilibrium, while their dynamical retrieval properties remain less well understood. In our previous work, we carried out a dynamical mean-field theory (DMFT) analysis of the Krotov--Hopfield-type dense associative memory and found that the transition between successful and failed retrieval is accompanied by pronounced slow dynamics. As a consequence, the effective basin of attraction observed in numerical simulations extends well beyond that predicted by equilibrium statistical mechanics. A natural hypothesis is that this discrepancy originates from diagonal (self-interaction) contributions in the Krotov--Hopfield model, which generate a large number of lower-order interaction terms and may induce glassy relaxation near the retrieval boundary. To test this hypothesis, we analyze an alternative high-order associative memory model, namely the Abbott--Arian-type $p$-body Hopfield model, in which such diagonal contributions are absent by construction. Using dynamical mean-field theory, we derive an effective single-site process together with closed macroscopic equations governing the retrieval dynamics. Our analysis reveals that both slow dynamics and a substantial enlargement of the apparent basin of attraction persist even in this model. These results indicate that the dynamical slowdown near the retrieval boundary cannot be attributed primarily to diagonal self-interaction effects, but instead originates from intrinsic properties of high-order interactions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑