Pith. sign in

Following the ground-states of full-RSB spherical spin glasses

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

We focus on spherical spin glasses whose Parisi distribution has support of the form $[0,q]$. For such models we construct paths from the origin to the sphere which consistently remain close to the ground-state energy on the sphere of corresponding radius. The construction uses a greedy strategy, which always follows a direction corresponding to the most negative eigenvalues of the Hessian of the Hamiltonian. For finite mixtures $\nu(x)$ it provides an algorithm of time complexity $O(N^{{\rm deg}(\nu)})$ to find w.h.p. points with the ground-state energy, up to a small error. For the pure spherical models, the same algorithm reaches the energy $-E_{\infty}$, the conjectural terminal energy for gradient descent. Using the TAP formula for the free energy, for full-RSB models with support $[0,q]$, we are able to prove the correct lower bound on the free energy (namely, prove the lower bound from Parisi's formula), assuming the correctness of the Parisi formula only in the replica symmetric case.

citation-role summary

background 1

citation-polarity summary

fields

math.PR 1

years

2019 1

verdicts

ACCEPT 1

roles

background 1

polarities

background 1

representative citing papers

The Overlap Gap Property in Principal Submatrix Recovery

math.PR · 2019-08-26 · accept · novelty 7.0

A sharp information-theoretic threshold for approximate recovery of a planted sparse submatrix is derived, and an overlap gap property is proved that blocks local MCMC algorithms in a conjecturally hard phase.

citing papers explorer

Showing 1 of 1 citing paper.

  • The Overlap Gap Property in Principal Submatrix Recovery math.PR · 2019-08-26 · accept · none · ref 79 · internal anchor

    A sharp information-theoretic threshold for approximate recovery of a planted sparse submatrix is derived, and an overlap gap property is proved that blocks local MCMC algorithms in a conjecturally hard phase.