深度神经网络中产生的随机矩阵:一般I.I.D.案例

IF 0.9 4区 数学 Q4 PHYSICS, MATHEMATICAL Random Matrices-Theory and Applications Pub Date : 2020-11-20 DOI:10.1142/s2010326322500460
L. Pastur, V. Slavin
{"title":"深度神经网络中产生的随机矩阵:一般I.I.D.案例","authors":"L. Pastur, V. Slavin","doi":"10.1142/s2010326322500460","DOIUrl":null,"url":null,"abstract":"We study the distribution of singular values of product of random matrices pertinent to the analysis of deep neural networks. The matrices resemble the product of the sample covariance matrices, however, an important difference is that the population covariance matrices assumed to be non-random or random but independent of the random data matrix in statistics and random matrix theory are now certain functions of random data matrices (synaptic weight matrices in the deep neural network terminology). The problem has been treated in recent work [25, 13] by using the techniques of free probability theory. Since, however, free probability theory deals with population covariance matrices which are independent of the data matrices, its applicability has to be justified. The justification has been given in [22] for Gaussian data matrices with independent entries, a standard analytical model of free probability, by using a version of the techniques of random matrix theory. In this paper we use another, more streamlined, version of the techniques of random matrix theory to generalize the results of [22] to the case where the entries of the synaptic weight matrices are just independent identically distributed random variables with zero mean and finite fourth moment. This, in particular, extends the property of the so-called macroscopic universality on the considered random matrices.","PeriodicalId":54329,"journal":{"name":"Random Matrices-Theory and Applications","volume":"13 1","pages":""},"PeriodicalIF":0.9000,"publicationDate":"2020-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"9","resultStr":"{\"title\":\"On Random Matrices Arising in Deep Neural Networks: General I.I.D. Case\",\"authors\":\"L. Pastur, V. Slavin\",\"doi\":\"10.1142/s2010326322500460\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We study the distribution of singular values of product of random matrices pertinent to the analysis of deep neural networks. The matrices resemble the product of the sample covariance matrices, however, an important difference is that the population covariance matrices assumed to be non-random or random but independent of the random data matrix in statistics and random matrix theory are now certain functions of random data matrices (synaptic weight matrices in the deep neural network terminology). The problem has been treated in recent work [25, 13] by using the techniques of free probability theory. Since, however, free probability theory deals with population covariance matrices which are independent of the data matrices, its applicability has to be justified. The justification has been given in [22] for Gaussian data matrices with independent entries, a standard analytical model of free probability, by using a version of the techniques of random matrix theory. In this paper we use another, more streamlined, version of the techniques of random matrix theory to generalize the results of [22] to the case where the entries of the synaptic weight matrices are just independent identically distributed random variables with zero mean and finite fourth moment. This, in particular, extends the property of the so-called macroscopic universality on the considered random matrices.\",\"PeriodicalId\":54329,\"journal\":{\"name\":\"Random Matrices-Theory and Applications\",\"volume\":\"13 1\",\"pages\":\"\"},\"PeriodicalIF\":0.9000,\"publicationDate\":\"2020-11-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"9\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Random Matrices-Theory and Applications\",\"FirstCategoryId\":\"100\",\"ListUrlMain\":\"https://doi.org/10.1142/s2010326322500460\",\"RegionNum\":4,\"RegionCategory\":\"数学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"PHYSICS, MATHEMATICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Random Matrices-Theory and Applications","FirstCategoryId":"100","ListUrlMain":"https://doi.org/10.1142/s2010326322500460","RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"PHYSICS, MATHEMATICAL","Score":null,"Total":0}
引用次数: 9

摘要

研究了与深度神经网络分析相关的随机矩阵乘积的奇异值分布。这些矩阵类似于样本协方差矩阵的乘积,然而,一个重要的区别是,在统计学和随机矩阵理论中被假设为非随机或随机但独立于随机数据矩阵的总体协方差矩阵现在是随机数据矩阵的某些函数(深度神经网络术语中的突触权重矩阵)。在最近的研究中[25,13]已经使用自由概率论的技术来处理这个问题。然而,由于自由概率论处理的是独立于数据矩阵的总体协方差矩阵,因此它的适用性必须得到证明。在[22]中,通过使用随机矩阵理论技术的一个版本,对具有独立条目的高斯数据矩阵(一种标准的自由概率分析模型)给出了证明。在本文中,我们使用另一种更精简的随机矩阵理论技术版本,将[22]的结果推广到突触权重矩阵的条目只是具有零平均值和有限第四矩的独立同分布随机变量的情况。特别地,这扩展了所谓的宏观通用性在所考虑的随机矩阵上的性质。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
On Random Matrices Arising in Deep Neural Networks: General I.I.D. Case
We study the distribution of singular values of product of random matrices pertinent to the analysis of deep neural networks. The matrices resemble the product of the sample covariance matrices, however, an important difference is that the population covariance matrices assumed to be non-random or random but independent of the random data matrix in statistics and random matrix theory are now certain functions of random data matrices (synaptic weight matrices in the deep neural network terminology). The problem has been treated in recent work [25, 13] by using the techniques of free probability theory. Since, however, free probability theory deals with population covariance matrices which are independent of the data matrices, its applicability has to be justified. The justification has been given in [22] for Gaussian data matrices with independent entries, a standard analytical model of free probability, by using a version of the techniques of random matrix theory. In this paper we use another, more streamlined, version of the techniques of random matrix theory to generalize the results of [22] to the case where the entries of the synaptic weight matrices are just independent identically distributed random variables with zero mean and finite fourth moment. This, in particular, extends the property of the so-called macroscopic universality on the considered random matrices.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Random Matrices-Theory and Applications
Random Matrices-Theory and Applications Decision Sciences-Statistics, Probability and Uncertainty
CiteScore
1.90
自引率
11.10%
发文量
29
期刊介绍: Random Matrix Theory (RMT) has a long and rich history and has, especially in recent years, shown to have important applications in many diverse areas of mathematics, science, and engineering. The scope of RMT and its applications include the areas of classical analysis, probability theory, statistical analysis of big data, as well as connections to graph theory, number theory, representation theory, and many areas of mathematical physics. Applications of Random Matrix Theory continue to present themselves and new applications are welcome in this journal. Some examples are orthogonal polynomial theory, free probability, integrable systems, growth models, wireless communications, signal processing, numerical computing, complex networks, economics, statistical mechanics, and quantum theory. Special issues devoted to single topic of current interest will also be considered and published in this journal.
期刊最新文献
Factoring determinants and applications to number theory Dynamics of a rank-one multiplicative perturbation of a unitary matrix Monotonicity of the logarithmic energy for random matrices Eigenvalue distributions of high-dimensional matrix processes driven by fractional Brownian motion Characteristic polynomials of orthogonal and symplectic random matrices, Jacobi ensembles & L-functions
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1