Imperial College London
Portrait Picture

DrWeiDai

Faculty of Engineering, Department of Electrical and Electronic Engineering

Senior Lecturer
 
 
 
//

Contact

 

+44 (0)20 7594 6333wei.dai1 Website

 
 
//

Location

 

811Electrical EngineeringSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Pitaval:2015:10.1109/TIT.2015.2448695,
author = {Pitaval, R-A and Dai, W and Tirkkonen, O},
doi = {10.1109/TIT.2015.2448695},
journal = {IEEE Transactions on Information Theory},
pages = {4451--4457},
title = {Convergence of Gradient Descent for Low-Rank Matrix Approximation},
url = {http://dx.doi.org/10.1109/TIT.2015.2448695},
volume = {61},
year = {2015}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - This paper provides a proof of global convergence of gradient search for low-rank matrix approximation. Such approximations have recently been of interest for large-scale problems, as well as for dictionary learning for sparse signal representations and matrix completion. The proof is based on the interpretation of the problem as an optimization on the Grassmann manifold and Fubiny-Study distance on this space.
AU  - Pitaval,R-A
AU  - Dai,W
AU  - Tirkkonen,O
DO  - 10.1109/TIT.2015.2448695
EP  - 4457
PY  - 2015///
SN  - 1557-9654
SP  - 4451
TI  - Convergence of Gradient Descent for Low-Rank Matrix Approximation
T2  - IEEE Transactions on Information Theory
UR  - http://dx.doi.org/10.1109/TIT.2015.2448695
UR  - http://hdl.handle.net/10044/1/40317
VL  - 61
ER  -
Download