Pith. sign in

REVIEW 1 cited by

Statistical mechanics of the maximum-average submatrix problem

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2303.05237 v2 pith:TFZS5RLN submitted 2023-03-09 cond-mat.dis-nn cs.ITmath.IT

Statistical mechanics of the maximum-average submatrix problem

classification cond-mat.dis-nn cs.ITmath.IT
keywords phasesubmatrixdiagramfindproblemaveragebreakingentries
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We study the maximum-average submatrix problem, in which given an $N \times N$ matrix $J$ one needs to find the $k \times k$ submatrix with the largest average of entries. We study the problem for random matrices $J$ 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 $k$ in the limit $N\to\infty$. We consider submatrices of size $k = m N$ with $0 < m < 1$. We find a rich phase diagram, including dynamical, static one-step replica symmetry breaking and full-step replica symmetry breaking. In the limit of $m \to 0$, 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.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Spectral Signatures of Replica Symmetry Breaking in Optimization-Induced Random Matrices

    cond-mat.dis-nn 2026-07 conditional novelty 7.0

    Difference spectra of two optimization-induced matrices from independent Gibbs samples form an explicit spectral transform of the Parisi overlap order parameter, while a single-matrix bulk is blind to replica symmetry...