Tensor completion via a multi-linear low-n-rank factorization model

Tensor completion via a multi-linear low-n-rank factorization model
复制标题

通过多线性低n阶分解模型完成张量

DOI:
10.1016/j.neucom.2013.11.020
复制
发表时间:
2014-06
期刊:
影响因子:
6
通讯作者:
Bin Ran
Bin Ran
中科院分区:
计算机科学2区
文献类型:
--
作者:
Bin Cheng;Wuhong Wang;Yu-Jin Zhang;Bin Ran

文献摘要

参考文献

被引文献

相似文献

张量完成问题是从其条目的子集中恢复低n阶张量。主要的解决策略是基于通过凸优化来最小化张量秩的迹范数的扩展。该策略承担奇异值分解(SVD)所需的计算成本,随着底层张量大小的增加,奇异值分解(SVD)变得越来越昂贵。为了降低计算成本,我们提出了一种多线性低n阶分解模型,并应用非线性高斯-塞达尔方法,每次迭代只需要求解一个线性最小二乘问题来求解该模型。数值结果表明,所提出的算法能够可靠地解决各种问题,速度至少比迹范数最小化算法快几倍。
The tensor completion problem is to recover a low-n-rank tensor from a subset of its entries. The main solution strategy has been based on the extensions of trace norm for the minimization of tensor rank via convex optimization. This strategy bears the computational cost required by the singular value decomposition (SVD) which becomes increasingly expensive as the size of the underlying tensor increase. In order to reduce the computational cost, we propose a multi-linear low-n-rank factorization model and apply the nonlinear Gauss–Seidal method that only requires solving a linear least squares problem per iteration to solve this model. Numerical results show that the proposed algorithm can reliably solve a wide range of problems at least several times faster than the trace norm minimization algorithm.
DOI: --
发表时间: 2010-10
期刊: arXiv: Machine Learning
影响因子: --
作者:
Ryota Tomioka;K. Hayashi;H. Kashima
通讯作者: Ryota Tomioka;K. Hayashi;H. Kashima
DOI: 10.1016/s0169-7439(00)00071-x
发表时间: 2000-08-14
影响因子: 3.9
作者:
Andersson, CA;Bro, R
通讯作者: Bro, R
DOI: 10.1109/cvpr.2006.141
发表时间: 2006-06
期刊: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
影响因子: --
作者:
N. Komodakis
通讯作者: N. Komodakis
DOI: --
发表时间: 2007
期刊: --
影响因子: --
作者:
Miklós Kurucz;A. Benczúr;Károly Csalogány
通讯作者: Miklós Kurucz;A. Benczúr;Károly Csalogány
DOI: --
发表时间: 2011
期刊: --
影响因子: --
作者:
Marco Signoretto;L. D. Lathauwer;J. Suykens
通讯作者: Marco Signoretto;L. D. Lathauwer;J. Suykens