Statistical mechanics of the maximum-average submatrix problem
Abstract
We study the maximum-average submatrix problem, in which given an matrix one needs to find the submatrix with the largest average of entries. We study the problem for random matrices whose entries are i.i.d. random variables by mapping it to a variant of the Sherrington-Kirkpatrick spin-glass model at fixed magnetization. We characterize analytically the phase diagram of the model as a function of the submatrix average and the size of the submatrix in the limit . We consider submatrices of size with . We find a rich phase diagram, including dynamical, static one-step replica symmetry breaking and full-step replica symmetry breaking. In the limit of , we find a simpler phase diagram featuring a frozen 1-RSB phase, where the Gibbs measure is composed of exponentially many pure states each with zero entropy. We discover an interesting phenomenon, reminiscent of the phenomenology of the binary perceptron: there exist efficient algorithms that provably work in the frozen 1-RSB phase.
Cite
@article{arxiv.2303.05237,
title = {Statistical mechanics of the maximum-average submatrix problem},
author = {Vittorio Erba and Florent Krzakala and Rodrigo Pérez and Lenka Zdeborová},
journal= {arXiv preprint arXiv:2303.05237},
year = {2024}
}