Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- articleJanuary 2018
Near-optimal stochastic approximation for online principal component estimation
Mathematical Programming: Series A and B (MPRG), Volume 167, Issue 1Pages 75–97https://doi.org/10.1007/s10107-017-1182-zPrincipal component analysis (PCA) has been a prominent tool for high-dimensional data analysis. Online algorithms that estimate the principal component by processing streaming data are of tremendous practical and theoretical interests. Despite its rich ...
- ArticleDecember 2017
Diffusion approximations for online principal component estimation and global convergence
NIPS'17: Proceedings of the 31st International Conference on Neural Information Processing SystemsPages 645–655In this paper, we propose to adopt the diffusion approximation tools to study the dynamics of Oja's iteration which is an online stochastic gradient descent method for the principal component analysis. Oja's iteration maintains a running estimate of the ...