Abstract | ||
---|---|---|
The low-rank matrix completion problem is fundamental to a number of tasks in data mining, machine learning, and signal processing. This paper considers the problem of adaptive matrix completion in time-varying scenarios. Given a sequence of incomplete and noise-corrupted matrices, the goal is to recover and track the underlying low rank matrices. Motivated from the classical least-mean square (LMS) algorithms for adaptive filtering, three LMS-like algorithms are proposed for estimating and tracking low-rank matrices. Performance of the proposed algorithms is provided in form of nonasymptotic bounds on the tracking mean-square error. Tracking performance of the algorithms is also studied via detailed simulations over real-world datasets. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/TSP.2017.2695450 | IEEE Trans. Signal Processing |
Keywords | Field | DocType |
Signal processing algorithms,Algorithm design and analysis,Heuristic algorithms,Approximation algorithms,Stochastic processes,Noise measurement,Sparse matrices | Approximation algorithm,Signal processing,Mathematical optimization,Matrix completion,Computer science,Matrix (mathematics),Theoretical computer science,Probabilistic analysis of algorithms,Low-rank approximation,Adaptive filter,Sparse matrix | Journal |
Volume | Issue | ISSN |
65 | 14 | 1053-587X |
Citations | PageRank | References |
4 | 0.43 | 32 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ruchi Tripathi | 1 | 7 | 1.50 |
Boda Mohan | 2 | 4 | 0.43 |
Ketan Rajawat | 3 | 124 | 25.44 |