Triplets of local minima in a high-dimensional random landscape: Correlations, clustering, and memoryless activated jumps

2024/10/23 by Pacco, Alessandro, Rosso, Alberto, Ros, Valentina · 1 citation
#Disordered Systems and Neural Networks (cond-mat.dis-nn) #FOS: Physical sciences #Statistical Mechanics (cond-mat.stat-mech)

paper · doi:10.48550/arxiv.2410.18010

Abstract

We compute the distribution of triplets of stationary points in the energy landscape of the spherical p-spin model, by evaluating the quenched three-point complexity by means of the Kac-Rice formalism. We show the occurrence of transitions in the organization of stationary points in the landscape, identifying regions where local minima and saddles accumulate and cluster around other stationary points, thus displaying the presence of correlations in the landscape. We discuss the implications of these findings for the dynamical exploration of the energy landscape in the activated regime, specifying conditions under which transitions between local minima are expected to exhibit correlated rates and when, conversely, activated jumps are likely to be memoryless.

Cited by

• Structure of solutions to continuous constraint satisfaction problems through the statistics of wedged and inscribed spheres

Related

• Exploring high-dimensional random landscapes: from spin glasses to random matrices, passing through simple chaotic systems
• The high-d landscapes paradigm: spin-glasses, and beyond
• Free energy landscapes in spherical spin glasses
• Curvature-driven pathways interpolating between stationary points: the case of the pure spherical 3-spin model
• The number of saddles of the spherical p-spin model