An algorithm for the principal component analysis of large data sets

Nathan Halko Per-Gunnar Martinsson Yoel Shkolnisky Mark Tygert

Published in: CoRR (2010)

Keyphrases

principal components
dynamic programming
improved algorithm
optimal solution
learning algorithm
cost function
probabilistic model
k means
search space
objective function
real world
preprocessing
simulated annealing
similarity measure
distance transform
face recognition
principal curves
maximum variance