A Random Algorithm for Low-Rank Decomposition of Large-Scale Matrices With Missing Entries

A random submatrix method (RSM) is proposed to calculate the low-rank decomposition U(m×r)V(n×r)(T) (r < m, n) of the matrix Y∈R(m×n) (assuming m > n generally) with known entry percentage 0 < ρ ≤ 1. RSM is very fast as only O(mr(2)ρ(r)) or O(n(3)ρ(3r)) floating-point operations (flops) are...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 24(2015), 11 vom: 24. Nov., Seite 4502-11
1. Verfasser: Liu, Yiguang (VerfasserIn)
Weitere Verfasser: Lei, Yinjie, Li, Chunguang, Xu, Wenzheng, Pu, Yifei
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2015
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Journal Article Research Support, Non-U.S. Gov't
LEADER 01000naa a22002652 4500
001 NLM251207110
003 DE-627
005 20231224161511.0
007 cr uuu---uuuuu
008 231224s2015 xx |||||o 00| ||eng c
024 7 |a 10.1109/TIP.2015.2458176  |2 doi 
028 5 2 |a pubmed24n0837.xml 
035 |a (DE-627)NLM251207110 
035 |a (NLM)26208344 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Liu, Yiguang  |e verfasserin  |4 aut 
245 1 2 |a A Random Algorithm for Low-Rank Decomposition of Large-Scale Matrices With Missing Entries 
264 1 |c 2015 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Completed 16.09.2015 
500 |a Date Revised 10.09.2015 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a A random submatrix method (RSM) is proposed to calculate the low-rank decomposition U(m×r)V(n×r)(T) (r < m, n) of the matrix Y∈R(m×n) (assuming m > n generally) with known entry percentage 0 < ρ ≤ 1. RSM is very fast as only O(mr(2)ρ(r)) or O(n(3)ρ(3r)) floating-point operations (flops) are required, compared favorably with O(mnr+r(2)(m+n)) flops required by the state-of-the-art algorithms. Meanwhile, RSM has the advantage of a small memory requirement as only max(n(2),mr+nr) real values need to be saved. With the assumption that known entries are uniformly distributed in Y, submatrices formed by known entries are randomly selected from Y with statistical size k×nρ(k) or mρ(l)×l , where k or l takes r+1 usually. We propose and prove a theorem, under random noises the probability that the subspace associated with a smaller singular value will turn into the space associated to anyone of the r largest singular values is smaller. Based on the theorem, the nρ(k)-k null vectors or the l-r right singular vectors associated with the minor singular values are calculated for each submatrix. The vectors ought to be the null vectors of the submatrix formed by the chosen nρ(k) or l columns of the ground truth of V(T). If enough submatrices are randomly chosen, V and U can be estimated accordingly. The experimental results on random synthetic matrices with sizes such as 13 1072 ×10(24) and on real data sets such as dinosaur indicate that RSM is 4.30 ∼ 197.95 times faster than the state-of-the-art algorithms. It, meanwhile, has considerable high precision achieving or approximating to the best 
650 4 |a Journal Article 
650 4 |a Research Support, Non-U.S. Gov't 
700 1 |a Lei, Yinjie  |e verfasserin  |4 aut 
700 1 |a Li, Chunguang  |e verfasserin  |4 aut 
700 1 |a Xu, Wenzheng  |e verfasserin  |4 aut 
700 1 |a Pu, Yifei  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society  |d 1992  |g 24(2015), 11 vom: 24. Nov., Seite 4502-11  |w (DE-627)NLM09821456X  |x 1941-0042  |7 nnns 
773 1 8 |g volume:24  |g year:2015  |g number:11  |g day:24  |g month:11  |g pages:4502-11 
856 4 0 |u http://dx.doi.org/10.1109/TIP.2015.2458176  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 24  |j 2015  |e 11  |b 24  |c 11  |h 4502-11