Streaming Principal Component Analysis in Noisy Setting

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.

Cite this Paper


BibTeX
@InProceedings{pmlr-v80-marinov18a, title = {Streaming Principal Component Analysis in Noisy Setting}, author = {Marinov, Teodor Vanislavov and Mianjy, Poorya and Arora, Raman}, booktitle = {Proceedings of the 35th International Conference on Machine Learning}, pages = {3413--3422}, year = {2018}, editor = {Dy, Jennifer and Krause, Andreas}, volume = {80}, series = {Proceedings of Machine Learning Research}, month = {10--15 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v80/marinov18a/marinov18a.pdf}, url = {http://proceedings.mlr.press/v80/marinov18a.html}, 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.} }
Endnote
%0 Conference Paper %T Streaming Principal Component Analysis in Noisy Setting %A Teodor Vanislavov Marinov %A Poorya Mianjy %A Raman Arora %B Proceedings of the 35th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jennifer Dy %E Andreas Krause %F pmlr-v80-marinov18a %I PMLR %P 3413--3422 %U http://proceedings.mlr.press/v80/marinov18a.html %V 80 %X 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.
APA
Marinov, T.V., Mianjy, P. & Arora, R.. (2018). Streaming Principal Component Analysis in Noisy Setting. Proceedings of the 35th International Conference on Machine Learning, in Proceedings of Machine Learning Research 80:3413-3422 Available from http://proceedings.mlr.press/v80/marinov18a.html.

Related Material