Dynamical properties of dense associative memory

ICLR 2026 Conference Submission24879 Authors

Keywords: Hopfield networks, dense associative memory, dynamics, convergence time, attraction basin, generating functional analysis

TL;DR: We analyze the recalling process using the generating functional analysis and discuss the convergence time and the attraction basins and so on.

Abstract: Dense associative memory, a fundamental instance of modern Hopfield networks, can store a large number of memory patterns as equilibrium states of recurrent networks. While the stationary-state storage capacity has been investigated, its dynamical properties have not yet been discussed. In this paper, we analyze the dynamics using an exact approach based on generating functional analysis. We show results on convergence properties of memory retrieval, such as the convergence time and the size of the attraction basins. Our analysis enables a quantitative evaluation of the convergence time and the storage capacity of dense associative memory, which is useful for model design. Unlike the traditional Hopfield model, the retrieval of a pattern does not act as additional noise to itself, suggesting that the structure of modern networks makes recall more robust. Furthermore, the methodology addressed here can be applied to other energy-based models, and thus has the potential to contribute to the design of future architectures.

Primary Area: learning theory

Submission Number: 24879