ML Anthology

Stochastic Optimization of PCA with Capped MSG

Raman Arora, Andy Cotter, Nati Srebro
NeurIPS 2013 pp. 1815-1823
/neurips/2013/arora2013neurips-stochastic/

Abstract

We study PCA as a stochastic optimization problem and propose a novel stochastic approximation algorithm which we refer to as Matrix Stochastic Gradient'' (MSG), as well as a practical variant, Capped MSG. We study the method both theoretically and empirically. "

PDF NeurIPS Semantic Scholar

Cite

Text

Arora et al. "Stochastic Optimization of PCA with Capped MSG." Neural Information Processing Systems, 2013.

Markdown

[Arora et al. "Stochastic Optimization of PCA with Capped MSG." Neural Information Processing Systems, 2013.](https://mlanthology.org/neurips/2013/arora2013neurips-stochastic/)

BibTeX

@inproceedings{arora2013neurips-stochastic,
  title     = {{Stochastic Optimization of PCA with Capped MSG}},
  author    = {Arora, Raman and Cotter, Andy and Srebro, Nati},
  booktitle = {Neural Information Processing Systems},
  year      = {2013},
  pages     = {1815-1823},
  url       = {https://mlanthology.org/neurips/2013/arora2013neurips-stochastic/}
}