Efficient Computation of Robust Weighted Low-Rank Matrix Approximations Using the L_1 Norm

By Anders P. Eriksson, Anton van den Hengel. 2012

67 citations recorded by the source corpus.

Subfields: Applied Mathematics, Artificial Intelligence, Optimization & Training, Numerical Methods & Scientific Computing, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Applied Mathematics

1. Yuanzhi Li
2. Yingyu Liang

In Artificial Intelligence

1. Yuanzhi Li
2. Yingyu Liang
3. Zeyuan Allen-Zhu
4. Andrej Risteski
5. Quanquan Gu
6. Tengyu Ma
7. Simon Shaolei Du
8. Jason D. Lee

In Optimization & Training

1. Yuanzhi Li
2. Yingyu Liang
3. Zeyuan Allen-Zhu
4. Andrej Risteski
5. Quanquan Gu
6. Tengyu Ma
7. Greg Yang
8. Zehao Dou

In Numerical Methods & Scientific Computing

1. Yuanzhi Li
2. Andrej Risteski
3. Yingyu Liang

In Signal Processing

1. Yuanzhi Li
2. Andrej Risteski
3. Yingyu Liang
4. Zeyuan Allen-Zhu

Citations in the corpus

• Recovery guarantee of weighted low-rank approximation via alternating minimization (2016, background): “Being a common practical problem (e.g., [Lu et al., 1997, Srebro and Jaakkola, 2003, Li et al., 2010, Eriksson and van den Hengel, 2012]), multiple heuristics for non-convexoptimization such as alternating minimization have been developed, but they come with no guarantees.”