Abstract
Mean-field spin glasses are families of random energy functions (Hamiltonians) on high-dimensional product spaces. In this paper, we consider the case of Ising mixed p-spin models,; namely, Hamiltonians on the Hamming hypercube , which are defined by the property that is a centered Gaussian process with covariance depending only on the scalar product .
The asymptotic value of the optimum was characterized in terms of a variational principle known as the Parisi formula, first proved by Talagrand and, in a more general setting, by Panchenko. The structure of superlevel sets is extremely rich and has been studied by a number of authors. Here, we ask whether a near optimal configuration σ can be computed in polynomial time.
We develop a message passing algorithm whose complexity per-iteration is of the same order as the complexity of evaluating the gradient of , and characterize the typical energy value it achieves. When the p-spin model satisfies a certain no-overlap gap assumption, for any , the algorithm outputs such that , with high probability. The number of iterations is bounded in N and depends uniquely on ε. More generally, regardless of whether the no-overlap gap assumption holds, the energy achieved is given by an extended variational principle, which generalizes the Parisi formula.
Funding Statement
This work was partially supported by NSF Grants CCF-1714305, IIS-1741162 and ONR N00014-18-1-2729.
Citation
Ahmed El Alaoui. Andrea Montanari. Mark Sellke. "Optimization of mean-field spin glasses." Ann. Probab. 49 (6) 2922 - 2960, November 2021. https://doi.org/10.1214/21-AOP1519
Information