arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1607.01668stat.MLcs.LGcs.NAmath.NA
收藏

用于信号处理和机器学习的张量分解

Tensor Decomposition for Signal Processing and Machine Learning

University of Minnesota(明尼苏达大学);KU Leuven(鲁汶大学);Carnegie Mellon University(卡内基梅隆大学)

Nicholas D. Sidiropoulos, Lieven De Lathauwer, Xiao Fu, Kejun Huang, Evangelos E. Papalexakis, Christos Faloutsos

摘要:

张量或{ \em multi-way arrays}是三个或更多索引$(i,j,k,\cdots)$的函数-类似于矩阵(双向数组),矩阵是(行,列)的两个索引$(r,c)$的函数。张量有着丰富的历史,绵延近一个世纪,涉及众多学科;但直到最近,它们才在信号处理、统计学、数据挖掘和机器学习的融合中,在信号和数据分析中变得无处不在。这篇概述文章旨在为有兴趣学习和使用张量的研究人员和从业者提供一个良好的起点。因此,它侧重于基础和动机(使用各种应用示例),旨在达到广度{ \em和深度}的适当平衡,这将使第一次参加矩阵代数和概率研究生课程的人能够开始进行研究和/或开发张量算法和软件。一些应用优化的背景是有用的,但不是严格要求的。所涵盖的材料包括张量秩和秩分解;基本张量分解模型及其关系和属性(包括相当好的可识别性覆盖);广泛覆盖从交替优化到随机梯度的算法;统计性能分析;以及从源分离到协同过滤,混合和主题建模,分类和多线性子空间学习的应用。

英文摘要:

Tensors or {\em multi-way arrays} are functions of three or more indices $(i,j,k,\cdots)$ -- similar to matrices (two-way arrays), which are functions of two indices $(r,c)$ for (row,column). Tensors have a rich history, stretching over almost a century, and touching upon numerous disciplines; but they have only recently become ubiquitous in signal and data analytics at the confluence of signal processing, statistics, data mining and machine learning. This overview article aims to provide a good starting point for researchers and practitioners interested in learning about and working with tensors. As such, it focuses on fundamentals and motivation (using various application examples), aiming to strike an appropriate balance of breadth {\em and depth} that will enable someone having taken first graduate courses in matrix algebra and probability to get started doing research and/or developing tensor algorithms and software. Some background in applied optimization is useful but not strictly required. The material covered includes tensor rank and rank decomposition; basic tensor factorization models and their relationships and properties (including fairly good coverage of identifiability); broad coverage of algorithms ranging from alternating optimization to stochastic gradient; statistical performance analysis; and applications ranging from source separation to collaborative filtering, mixture and topic modeling, classification, and multilinear subspace learning.

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。

↑