arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1809.00535math.NAcs.NA
收藏

张量网络用于潜在变量分析:高阶canonical polyadic分解

Tensor Networks for Latent Variable Analysis: Higher Order Canonical Polyadic Decomposition

Skolkovo Institute of Science and Technology (Skoltech)(斯科尔科沃科学技术学院);Imperial College(帝国理工学院)

Anh-Huy Phan, Andrzej Cichocki, Ivan Oseledets, Salman Ahmadi Asl, Giuseppe Calvi, Danilo Mandic

AI总结:

本文提出一种基于张量网络的高阶CPD方法,通过低复杂度迭代算法解决高阶张量分解的计算成本和排列问题。

摘要:

canonical polyadic分解(CPD)是一种方便直观的张量分解工具;然而,对于高阶张量,它往往表现出高计算成本和张量元素的排列,这些不利影响随着张量阶数呈指数增长。现有张量压缩可以降低CPD的计算成本,但仅适用于分解阶数R不超过张量维度的情况。为了解决这些问题,我们提出了一种新的高阶张量CPD方法,该方法基于一个简单的张量网络,该网络由阶数不超过3的代表性相互连接的核心张量组成。为保证严谨性,我们开发了从核心张量到CPD因子矩阵的精确转换方案,并开发了一个低复杂度的迭代算法来估计这些因子矩阵(在不精确的情况下)。全面的模拟在各种场景中支持了该方法。

英文摘要:

The Canonical Polyadic decomposition (CPD) is a convenient and intuitive tool for tensor factorization; however, for higher-order tensors, it often exhibits high computational cost and permutation of tensor entries, these undesirable effects grow exponentially with the tensor order. Prior compression of tensor in-hand can reduce the computational cost of CPD, but this is only applicable when the rank $R$ of the decomposition does not exceed the tensor dimensions. To resolve these issues, we present a novel method for CPD of higher-order tensors, which rests upon a simple tensor network of representative inter-connected core tensors of orders not higher than 3. For rigour, we develop an exact conversion scheme from the core tensors to the factor matrices in CPD, and an iterative algorithm with low complexity to estimate these factor matrices for the inexact case. Comprehensive simulations over a variety of scenarios support the approach.

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。

↑