arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.12939math.PRcond-mat.dis-nncs.ITcs.LGmath-phmath.ITmath.MP
收藏

高维无序对数凹Gibbs测度的强副本对称性

Strong replica symmetry for high-dimensional disordered log-concave Gibbs measures

The Abdus Salam International Center for Theoretical Physics(阿卜杜勒·萨拉姆国际理论物理中心);University of Toronto(多伦多大学)

Jean Barbier, Dmitry Panchenko, Manuel Sáenz

摘要:

我们考虑一类通用的对数凹(可能是随机的)(吉布斯)度量。我们证明了浓度的一个无限家庭的顺序参数称为多重重叠。因为它们完全参数化了系统的猝灭吉布斯测度,这意味着渐近吉布斯测度的简单表示,以及强意义上的变量解耦。这些结果可能证明自己在几个方面是有用的。特别是在机器学习和高维推理中,对数凹度量出现在凸经验风险最小化、最大后验推理或M估计中。我们相信,他们可能是适用于建立某种类型的“副本对称公式”的自由能,推断或泛化错误,在这样的设置。

英文摘要:

We consider a generic class of log-concave, possibly random, (Gibbs) measures. We prove the concentration of an infinite family of order parameters called multioverlaps. Because they completely parametrise the quenched Gibbs measure of the system, this implies a simple representation of the asymptotic Gibbs measures, as well as the decoupling of the variables in a strong sense. These results may prove themselves useful in several contexts. In particular in machine learning and high-dimensional inference, log-concave measures appear in convex empirical risk minimisation, maximum a-posteriori inference or M-estimation. We believe that they may be applicable in establishing some type of "replica symmetric formulas" for the free energy, inference or generalisation error in such settings.

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。

↑