Paper ID sheet UCL-INMA-2018.09


Preconditioned conjugate gradient algorithms for graph regularized matrix completion

Shuyu Dong, P.-A. Absil, Kyle A. Gallivan
Low-rank matrix completion is the problem of recovering the missing entries of a data matrix by using the assumption that a good low-rank approximation to the true matrix is possible. Much attention has been paid recently to exploiting correlations between the column/row enti- ties through side information to improve the matrix completion quality. In this paper, we propose an effcient algorithm for solving the low-rank ma- trix completion with graph-based regularizers. Experiments on synthetic data show that our approach achieves significant speedup compared to the alternating minimization scheme.
Key words
Proceedings of the ESANN 2019 conference, to appear