Fetching the paper…
Reading the bibliography…
We study the problem of recovering the subspace spanned by the first $k$ principal components of $d$-dimensional data under the streaming setting, with a memory bound of $O(kd)$.
On stochastic approximation of the eigenvectors and eigenvalues of the expectation of a random matrix
Oja, E. and Karhunen, J. (1985) · 1985
Earlier work this paper cites.
Asymptotic theory of finite-dimensional normed spaces
Milman, V. D. and Schechtman, G. (1986) · 1986
Earlier work this paper cites.
Matrix Computations (3rd Ed.)
Golub, G. H. and Van Loan, C. F. (1996) · 1996
Earlier work this paper cites.
Randomized Online PCA Algorithms with Regret Bounds that are Logarithmic in the Dimension
Warmuth, M. K. and Kuzmin, D. (2008) · 2008
Earlier work this paper cites.
Stochastic optimization for pca and pls
Arora, R., Cotter, A., Livescu, K., and Srebro, N. (2012) · 2012
Earlier work this paper cites.
Making gradient descent optimal for strongly convex stochastic optimization
Rakhlin, A., Shamir, O., and Sridharan, K. (2012) · 2012
Cited alongside, same era.
Stochastic optimization of pca with capped msg
Arora, R., Cotter, A., and Srebro, N. (2013) · 2013
Cited alongside, same era.
UCI machine learning repository
Bache, K. and Lichman, M. (2013) · 2013
Cited alongside, same era.
The fast convergence of incremental pca
Balsubramani, A., Dasgupta, S., and Freund, Y. (2013) · 2013
Cited alongside, same era.
Memory limited, streaming pca
Mitliagkas, I., Caramanis, C., and Jain, P. (2013) · 2013
Cited alongside, same era.
Online pca with optimal regrets
Nie, J., Kotlowski, W., and Warmuth, M. K. (2013) · 2013
Later among the works it cites.
The noisy power method: A meta algorithm with applications
Hardt, M. and Price, E. (2014) · 2014
Later among the works it cites.
Online pca with spectral bounds
Karnin, Z. and Liberty, E. (2015) · 2015
Closest in time.
Global convergence of stochastic gradient descent for some non-convex matrix problems
Sa, C. D., Re, C., and Olukotun, K. (2015) · 2015
Closest in time.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…