Average performance analysis of the stochastic gradient method for online PCA
This work addresses computational efficiency for online PCA in streaming applications, but it is incremental as it builds on existing stochastic gradient methods.
The paper tackles the complexity of stochastic gradient descent for online PCA in streaming data and proposes an online learning rate selection method, with simulation experiments showing practical relevance and drastic improvements from learning the learning rate.
This paper studies the complexity of the stochastic gradient algorithm for PCA when the data are observed in a streaming setting. We also propose an online approach for selecting the learning rate. Simulation experiments confirm the practical relevance of the plain stochastic gradient approach and that drastic improvements can be achieved by learning the learning rate.