Streaming Principal Component Analysis in Noisy Setting

[edit]

Teodor Vanislavov Marinov, Poorya Mianjy, Raman Arora ;
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:3413-3422, 2018.

Abstract

We study streaming algorithms for principal component analysis (PCA) in noisy settings. We present computationally efficient algorithms with sub-linear regret bounds for PCA in the presence of noise, missing data, and gross outliers.

Related Material