arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.05237cond-mat.dis-nncs.ITmath.IT
收藏

最大平均子矩阵问题的统计力学

Statistical mechanics of the maximum-average submatrix problem

Vittorio Erba, Florent Krzakala, Rodrigo Pérez, Lenka Zdeborová

AI总结:

本文将随机矩阵的最大平均子矩阵问题映射为固定磁化的 Sherrington–Kirkpatrick 模型,解析其相图并发现冻结 1-RSB 相中存在可证明有效的算法。

摘要:

我们研究最大平均子矩阵问题:给定一个 $N \times N$ 矩阵 $J$,需要找到其元素平均值最大的 $k \times k$ 子矩阵。我们针对元素为独立同分布随机变量的随机矩阵 $J$ 研究该问题,方法是将其映射为固定磁化强度下 Sherrington–Kirkpatrick 自旋玻璃模型的一个变体。在 $N\to\infty$ 极限下,我们以子矩阵平均值和子矩阵尺寸 $k$ 为变量,解析地刻画了该模型的相图。我们考虑尺寸为 $k=mN$、其中 $0<m<1$ 的子矩阵。我们发现了丰富的相图,包括动力学相、静态一步副本对称性破缺相和全步副本对称性破缺相。在 $m\to0$ 极限下,我们发现更简单的相图,其特征是冻结的 1-RSB 相:Gibbs 测度由指数多个纯态组成,而每个纯态的熵均为零。我们发现了一个令人感兴趣的现象,令人联想到 binary perceptron 的现象学:存在一些高效算法,可证明在冻结的 1-RSB 相中有效。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑