Entrywise concentration bounds, a central limit theorem, and a median-of-means variance estimator give linear-time coordinate-wise uncertainty quantification for streaming PCA with Oja's algorithm.
First efficient convergence for streaming k-pca: a global, gap-free, and near-optimal rate
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.ST 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Beyond Sin-Squared Error: Linear-Time Entrywise Uncertainty Quantification for Streaming PCA
Entrywise concentration bounds, a central limit theorem, and a median-of-means variance estimator give linear-time coordinate-wise uncertainty quantification for streaming PCA with Oja's algorithm.