Random Matrices and complexity of Spin Glasses

Abstract

We give an asymptotic evaluation of the complexity of spherical p-spin spin-glass models via random matrix theory. This study enables us to obtain detailed information about the bottom of the energy landscape, including the absolute minimum (the ground state), the other local minima, and describe an interesting layered structure of the low critical values for the Hamiltonians of these models. We also show that our approach allows us to compute the related TAP-complexity and extend the results known in the physics literature. As an independent tool, we prove a LDP for the k-th largest eigenvalue of the GOE, extending the results of Ben Arous, Dembo and Guionnett (2001).

25 pages, 1 figure, references added

References in corpus (2)

• Phase space geometry and slow dynamics
• On the overlap in the multiple spherical SK models

Cited by in corpus (7)

• The Loss Surfaces of Multilayer Networks
• Betti numbers of random real hypersurfaces and determinants of random symmetric matrices
• Free energy and complexity of spherical bipartite models
• On the number of connected components of random algebraic hypersurfaces
• Rethinking generalization requires revisiting old ideas: statistical mechanics approaches and complex learning behavior
• Random Morse functions and spectral geometry
• Towards Prediction of Financial Crashes with a D-Wave Quantum Computer