Recovering PCA from Hybrid- Sparse Sampling of Data Elements

This paper addresses how well we can recover a data matrix when only given a few of its elements. We present a randomized algorithm that element-wise sparsifies the data, retaining only a few its elements. Our new algorithm independently samples the data using sampling probabilities that depend on both the squares ( sampling) and absolute values ( sampling) of the entries. We prove that the hybrid algorithm recovers a near-PCA reconstruction of the data from a sublinear sample-size: hybrid-() inherits the -ability to sample the important elements as well as the regularization properties of sampling, and gives strictly better performance than either or on their own. We also give a one-pass version of our algorithm and show experiments to corroborate the theory.
View on arXiv