arXiv Analytics

Sign in

arXiv:2303.06375 [cond-mat.dis-nn]AbstractReferencesReviewsResources

About the de Almeida-Thouless line in neural networks

Linda Albanese, Adriano Barra, Alessia Annibale

Published 2023-03-11Version 1

In this work we present a rigorous and straightforward method to detect the onset of the instability of replica-symmetric theories in information processing systems, which does not require a full replica analysis as in the method originally proposed by Almeida-Thouless for spin glasses. The method is based on an expansion of the free-energy obtained within one-step of the replica symmetry breaking (RSB) scheme around the replica-symmetric (RS) value. As such, it requires solely continuity and differentiability of the free-energy and it is robust to be applied broadly to systems with quenched disorder. We apply the method to the Hopfield model and to neural networks with multi-node Hebbian interactions, as case studies. In the appendix we test the method on the Sherrington-Kirkpatrick, the Ising P-spin and the spherical P-spin models, recovering the AT lines known in the literature for these models, as a special limit, which corresponds to assuming that the transition from the RS to the RSB phase can be obtained by varying continuously the order parameters. Therefore, our method provides a generalization of the AT approach, which can be applied to systems with a discontinuous transition.

Related articles: Most relevant | Search more
arXiv:1206.4492 [cond-mat.dis-nn] (Published 2012-06-20)
The 1/m expansion in spin glasses and the de Almeida-Thouless line
arXiv:2309.09240 [cond-mat.dis-nn] (Published 2023-09-17)
High-dimensional manifold of solutions in neural networks: insights from statistical physics
arXiv:cond-mat/0601248 (Published 2006-01-12, updated 2007-01-06)
Aging behavior of spin glasses under bond and temperature perturbations from laser illumination