arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.25440cond-mat.dis-nncond-mat.stat-mechcs.LG
收藏

对称感知机:教师-学生场景

The Symmetric Perceptron: a Teacher-Student Scenario

Institute for Cross-disciplinary Physics and Complex Systems IFISC (CSIC-UIB), Campus Universitat Illes Balears, 07122 Palma de Mallorca, Spain(跨学科物理与复杂系统研究所 IFISC(CSIC-UIB),巴利阿里大学校区,西班牙帕尔马);Université Paris-Saclay, CNRS, INRIA Tau team, LISN, 91190 Gif-sur-Yvette, France(巴黎-萨克雷大学,法国国家科学研究中心,INRIA Tau团队,LISN,法国吉夫-苏尔-伊维特);Indian Institute of Science Education and Research, Bhopal 462066, India(印度科学教育与研究院,博帕尔)

Giovanni Catania, Aurélien Decelle, Suhanee Korpe

AI总结:

本文提出并解决对称二元感知机的教师-学生模型,将其转化为具有保证解的种植推断问题。通过引入双区域标签,分析噪声less示例的贝叶斯最优情况及热噪声影响,揭示学习过程中的二级不稳定性及向完全对齐的首次相变。

摘要:

我们介绍了并解决了对称二元感知机的教师-学生模型,将其从传统存储导向模型转变为具有保证解的种植推断问题。我们调整了传统上考虑u形势能或矩形势能的对称感知机模型,通过在两个区域中包含标签。利用高维极限下的退火和淬火自由熵计算,我们绘制了三个控制参数(样本密度α、原点到对称超平面的距离κ和温度T)的相图,并识别出一个鲁棒场景,其中学习由二级不稳定性产生教师相关次优状态,随后通过首次相变实现完全对齐。我们展示了该结构如何依赖于势能的选择,以及次优解的亚稳态与向种植配置熔化的相互作用,这对基于蒙特卡罗的优化算法具有相关性。

英文摘要:

We introduce and solve a teacher-student formulation of the symmetric binary Perceptron, turning a traditionally storage-oriented model into a planted inference problem with a guaranteed solution at any sample density. We adapt the formulation of the symmetric Perceptron which traditionally considers either the u-shaped potential or the rectangular one, by including labels in both regions. With this formulation, we analyze both the Bayes-optimal regime at for noise-less examples and the effect of thermal noise under two different potential/classification rules. Using annealed and quenched free-entropy calculations in the high-dimensional limit, we map the phase diagram in the three control parameters, namely the sample density $α$, the distance between the origin and one of the symmetric hyperplanes $κ$ and temperature $T$, and identify a robust scenario where learning is organized by a second-order instability that creates teacher-correlated suboptimal states, followed by a first-order transition to full alignment. We show how this structure depends on the choice of potential, the interplay between metastability of the suboptimal solution and its melting towards the planted configuration, which is relevant for Monte Carlo-based optimization algorithms.

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。

↑