The paper proves an upper bound convergence rate for an adaptive two-measurement streaming PCA algorithm, and claims, without a proof in the text, that this rate is optimal.
The Fast Convergence of Incremental PCA
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We consider a situation in which we see samples in $\mathbb{R}^d$ drawn i.i.d. from some distribution with mean zero and unknown covariance A. We wish to compute the top eigenvector of A in an incremental fashion - with an algorithm that maintains an estimate of the top eigenvector in O(d) space, and incrementally adjusts the estimate with each new data point that arrives. Two classical such schemes are due to Krasulina (1969) and Oja (1983). We give finite-sample convergence rates for both.
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Global Convergence of Adaptive Sensing for Principal Eigenvector Estimation
The paper proves an upper bound convergence rate for an adaptive two-measurement streaming PCA algorithm, and claims, without a proof in the text, that this rate is optimal.