Randomized Online CP Decomposition

Submitted by grigby1 on Mon, 08/12/2019 - 3:23pm

Title	Randomized Online CP Decomposition
Publication Type	Conference Paper
Year of Publication	2018
Authors	Ma, C., Yang, X., Wang, H.
Conference Name	2018 Tenth International Conference on Advanced Computational Intelligence (ICACI)
Publisher	IEEE
ISBN Number	978-1-5386-4362-4
Keywords	CANDECOMP/PARAFAC decomposition, compositionality, Computational Intelligence, CP decomposition, Cyber physical system, decomposition, Handheld computers, large-scale tensors, Matrix decomposition, Metrics, online CP decomposition algorithm, online learning, pubcrawl, randomized online CP decomposition, randomized-sampling, randomized-sampling CP decomposition algorithm, ROCP algorithm, tensor decomposition, tensors
Abstract	CANDECOMP/PARAFAC (CP) decomposition has been widely used to deal with multi-way data. For real-time or large-scale tensors, based on the ideas of randomized-sampling CP decomposition algorithm and online CP decomposition algorithm, a novel CP decomposition algorithm called randomized online CP decomposition (ROCP) is proposed in this paper. The proposed algorithm can avoid forming full Khatri-Rao product, which leads to boost the speed largely and reduce memory usage. The experimental results on synthetic data and real-world data show the ROCP algorithm is able to cope with CP decomposition for large-scale tensors with arbitrary number of dimensions. In addition, ROCP can reduce the computing time and memory usage dramatically, especially for large-scale tensors.
URL	https://ieeexplore.ieee.org/document/8377495
DOI	10.1109/ICACI.2018.8377495
Citation Key	ma_randomized_2018

Groups:

Science of Security VO