Universality in bipartite mean field spin glasses

Abstract

In this work we give a proof of universality with respect to the choice of the statistical distribution of the quenched noise, for mean field bipartite spin glasses. We use mainly techniques of spin glasses theory, as Guerra's interpolation and the cavity approach. As a direct conseguence of our results, we have a proof of convergence in the sup norm of the free energy of the Hopfield Model to its expectation value.

References in corpus (5)

• Broken Replica Symmetry Bounds in the Mean Field Spin Glass Model
• Multitasking associative networks
• Equilibrium statistical mechanics of bipartite spin systems
• A simple invariance theorem
• Bipartite Mean Field Spin Systems. Existence and Solution

Cited by in corpus (13)

• Phase Diagram of Restricted Boltzmann Machines and Generalised Hopfield Networks with Arbitrary Priors
• Replica Symmetry Breaking in Bipartite Spin Glasses and Neural Networks
• Neural networks with redundant representation: detecting the undetectable
• Dreaming neural networks: rigorous results
• Neural Networks retrieving Boolean patterns in a sea of Gaussian ones
• Replica symmetry breaking in dense neural networks
• Dense Hebbian neural networks: a replica symmetric picture of supervised learning
• Legendre Duality of Spherical and Gaussian Spin Glasses
• Free energies of Boltzmann Machines: self-averaging, annealed and replica symmetric approximations in the thermodynamic limit
• Non-linear PDEs approach to statistical mechanics of Dense Associative Memories
• Interpolating between boolean and extremely high noisy patterns through Minimal Dense Associative Memories
• Pattern recognition in Deep Boltzmann machines
• Universality of chaos and ultrametricity in mixed p-spin models