In this section
@article{Cichocki:2016:10.1561/2200000059,
author = {Cichocki, A and Lee, N and Oseledets, I and Phan, A-H and Zhao, Q and Mandic, DP},
doi = {10.1561/2200000059},
journal = {Foundations and Trends in Machine Learning},
pages = {249--429},
title = {Tensor Networks for Dimensionality Reduction and Large-scale Optimization: Part 1 Low-Rank Tensor Decompositions},
url = {http://dx.doi.org/10.1561/2200000059},
volume = {9},
year = {2016}
}
TY - JOUR
AB - Modern applications in engineering and data science are increasingly based on multidimensional data of exceedingly high volume, variety, and structural richness. However, standard machine learning algorithms typically scale exponentially with data volume and complexity of cross-modal couplings - the so called curse of dimensionality - which is prohibitive to the analysis of large-scale, multi-modal and multi-relational datasets. Given that such data are often efficiently represented as multiway arrays or tensors, it is therefore timely and valuable for the multidisciplinary machine learning and data analytic communities to review low-rank tensor decompositions and tensor networks as emerging tools for dimensionality reduction and large scale optimization problems. Our particular emphasis is on elucidating that, by virtue of the underlying low-rank approximations, tensor networks have the ability to alleviate the curse of dimensionality in a number of applied areas. In Part 1 of this monograph we provide innovative solutions to low-rank tensor network decompositions and easy to interpret graphical representations of the mathematical operations on tensor networks. Such a conceptual insight allows for seamless migration of ideas from the flat-view matrices to tensor network operations and vice versa, and provides a platform for further developments, practical applications, and non-Euclidean extensions. It also permits the introduction of various tensor network operations without an explicit notion of mathematical expressions, which may be beneficial for many research communities that do not directly rely on multilinear algebra. Our focus is on the Tucker and tensor train (TT) decompositions and their extensions, and on demonstrating the ability of tensor networks to provide linearly or even super-linearly (e.g., logarithmically) scalable solutions, as illustrated in detail in Part 2 of this monograph.
AU - Cichocki,A
AU - Lee,N
AU - Oseledets,I
AU - Phan,A-H
AU - Zhao,Q
AU - Mandic,DP
DO - 10.1561/2200000059
EP - 429
PY - 2016///
SN - 1935-8237
SP - 249
TI - Tensor Networks for Dimensionality Reduction and Large-scale Optimization: Part 1 Low-Rank Tensor Decompositions
T2 - Foundations and Trends in Machine Learning
UR - http://dx.doi.org/10.1561/2200000059
VL - 9
ER -
