Online (and Offline) Robust PCA: Novel Algorithms and Performance Guarantees


Jinchun Zhan, Brian Lois, Han Guo, Namrata Vaswani ;
Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, PMLR 51:1488-1496, 2016.


In this work we develop and study a novel online robust principal components’ analysis (RPCA) algorithm based on the recently introduced ReProCS framework. Our algorithm significantly improves upon the original ReProCS algorithm and it also returns even more accurate offline estimates. The key contribution of this work is a correctness result for this algorithm under relatively mild assumptions. By using extra (but usually valid) assumptions we are able to remove one important limitation of batch RPCA results and two important limitations of a recent result for ReProCS for online RPCA. To the best of our knowledge, this work is among the first correctness results for online RPCA.

Related Material