Online Learning for Sparse PCA in High Dimensions: Exact Dynamics and Phase Transitions

Author name not available (Why is that?)

Publication date: 7 September 2016

Abstract: We study the dynamics of an online algorithm for learning a sparse leading eigenvector from samples generated from a spiked covariance model. This algorithm combines the classical Oja's method for online PCA with an element-wise nonlinearity at each iteration to promote sparsity. In the high-dimensional limit, the joint empirical measure of the underlying sparse eigenvector and its estimate provided by the algorithm is shown to converge weakly to a deterministic, measure-valued process. This scaling limit is characterized as the unique solution of a nonlinear PDE, and it provides exact information regarding the asymptotic performance of the algorithm. For example, performance metrics such as the cosine similarity and the misclassification rate in sparse support recovery can be obtained by examining the limiting dynamics. A steady-state analysis of the nonlinear PDE also reveals an interesting phase transition phenomenon. Although our analysis is asymptotic in nature, numerical simulations show that the theoretical predictions are accurate for moderate signal dimensions.

Has companion code repository: https://github.com/ceteke/sparse-pca

This page was built for publication: Online Learning for Sparse PCA in High Dimensions: Exact Dynamics and Phase Transitions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6277282)