arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1606.04142cs.ITcond-mat.dis-nncs.LGmath-phmath.ITmath.MP
收藏

对称秩1矩阵估计的互信息:副本公式的证明

Mutual information for symmetric rank-one matrix estimation: A proof of the replica formula

Ecole Polytechnique Fédérale de Lausanne(洛桑联邦理工学院);CNRS(法国国家科学研究中心);PSL Universités et Ecole Normale Supérieure(巴黎文理研究大学和巴黎高等师范学院);Sorbonne Universités et Université Pierre & Marie Curie(索邦大学和皮埃尔和玛丽居里大学);CEA(法国原子能和替代能源委员会);Université Paris-Saclay(巴黎萨克雷大学)

Jean Barbier, Mohamad Dia, Nicolas Macris, Florent Krzakala, Thibault Lesieur, Lenka Zdeborova

摘要:

分解低秩矩阵在机器学习和统计学中有许多应用。对于贝叶斯最优设置下的概率模型,利用启发式统计物理计算提出了互信息的一般表达式,并在一些特定情况下得到了证明。在这里,我们展示了如何严格证明对称秩一情况下的约束公式。这允许表达的最小均方误差,并在一个大的估计问题,范围从社区发现稀疏PCA的可检测性相变的特征。我们还表明,对于一个大的参数集,称为近似消息传递的迭代算法是贝叶斯最优的。然而,在目前已知的多项式算法所能做的与理论上所期望的信息之间存在差距。此外,证明技术有自己的兴趣,并利用三个基本成分:Guerra在统计物理学中引入的插值方法,近似消息传递算法的分析以及编码中的空间耦合和阈值饱和理论。我们的方法是通用的,适用于其他开放的问题,在统计估计启发式统计物理预测。

英文摘要:

Factorizing low-rank matrices has many applications in machine learning and statistics. For probabilistic models in the Bayes optimal setting, a general expression for the mutual information has been proposed using heuristic statistical physics computations, and proven in few specific cases. Here, we show how to rigorously prove the conjectured formula for the symmetric rank-one case. This allows to express the minimal mean-square-error and to characterize the detectability phase transitions in a large set of estimation problems ranging from community detection to sparse PCA. We also show that for a large set of parameters, an iterative algorithm called approximate message-passing is Bayes optimal. There exists, however, a gap between what currently known polynomial algorithms can do and what is expected information theoretically. Additionally, the proof technique has an interest of its own and exploits three essential ingredients: the interpolation method introduced in statistical physics by Guerra, the analysis of the approximate message-passing algorithm and the theory of spatial coupling and threshold saturation in coding. Our approach is generic and applicable to other open problems in statistical estimation where heuristic statistical physics predictions are available.

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。

↑