-norm low-rank linear approximation for accelerating deep neural networks
Authors:
- Zhiqun ZhaoZZZhiqun Zhao
- Hengyou WangHWHengyou Wang
- Hao SunHSHao Sun
- Zhihai HeZHZhihai He
- 1 August 2020
- journal article
- research article
- Published by Elsevier in Neurocomputing
- Vol. 400, 216-226
Abstract
No abstract availableKeywords
Funding Information
- National Natural Science Foundation of China (61971290)
This publication has 12 references indexed in Scilit:
- Robust Generalized Low-Rank Decomposition of Multimatrices for Image RecoveryIEEE Transactions on Multimedia, 2016
- Accelerating Very Deep Convolutional Networks for Classification and DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- Robust Generalized Low Rank Approximations of MatricesPLOS ONE, 2015
- Robust principal component analysis?Journal of the ACM, 2011
- A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse ProblemsSIAM Journal on Imaging Sciences, 2009
- Regularized linear and kernel redundancy analysisComputational Statistics & Data Analysis, 2007
- Constrained Principal Component Analysis: A Comprehensive TheoryApplicable Algebra in Engineering, Communication and Computing, 2001
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- A L 1-norm PCA and a Heuristic Approach1996
- On the Douglas—Rachford splitting method and the proximal point algorithm for maximal monotone operatorsMathematical Programming, 1992