arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.04479cond-mat.dis-nncond-mat.stat-mechmath-phmath.MP
收藏

如何在对称二值感知机中逃离非典型区域:一场穿越连通解状态的旅程

How to escape atypical regions in the symmetric binary perceptron: a journey through connected-solutions states

Damien Barbier

AI总结:

本文研究二值对称感知机的非典型解,提出统计度量探测连通解序列,发现具有Markovian相关性的连通状态仅在特定阈值下能完全去相关,并引入嵌套Markov链分析非平凡相关性分布。

摘要:

我们研究二值对称感知机模型,特别是其非典型解。虽然该问题的解空间主要由孤立构型主导,但在特定的约束密度 $α$ 和阈值 $κ$ 范围内它也是可解的。本文提供了一种统计度量来探测解序列,其中两个连续元素具有强重叠。经过简化,我们通过将其与 Monte-Carlo 模拟进行比较来测试其预测。我们获得了良好的一致性,并表明具有 Markovian 相关性分布的连通状态只有在 $κ>κ_{\rm no-mem.\\, state}$ 时才能与其初始化完全去相关(对于 $α=0.5$ 且 $N$ 为问题维度的情况,$κ_{\rm no-mem.\\, state}\sim \sqrt{0.91\log(N)}$)。对于 $κ<κ_{\rm no-mem.\\, state}$,我们表明去相关序列仍然存在,但具有非平凡的相关性分布。为了研究这一状态,我们引入了一种相关性 $Ansatz$,我们将其标记为嵌套 Markov 链。

英文摘要:

We study the binary symmetric perceptron model, and in particular its atypical solutions. While the solution-space of this problem is dominated by isolated configurations, it is also solvable for a certain range of constraint density $α$ and threshold $κ$. We provide in this paper a statistical measure probing sequences of solutions, where two consecutive elements shares a strong overlap. After simplifications, we test its predictions by comparing it to Monte-Carlo simulations. We obtain good agreement and show that connected states with a Markovian correlation profile can fully decorrelate from their initialization only for $κ>κ_{\rm no-mem.\, state}$ ($κ_{\rm no-mem.\, state}\sim \sqrt{0.91\log(N)}$ for $α=0.5$ and $N$ being the dimension of the problem). For $κ<κ_{\rm no-mem.\, state}$, we show that decorrelated sequences still exist but have a non-trivial correlations profile. To study this regime we introduce an $Ansatz$ for the correlations that we label as the nested Markov chain.

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。

↑