Improving approximate RPCA with a k-sparsity prior

TL;DR

This paper enhances approximate robust PCA by incorporating a k-sparsity prior, leading to more parsimonious representations and improved performance in classification tasks.

Contribution

It introduces a k-sparsity prior into the neural network-based approximate RPCA, addressing local minima issues and improving representation quality.

Findings

Improved classification accuracy with k-sparsity prior

More parsimonious data representations

Outperforms original approximate RPCA

Abstract

A process centric view of robust PCA (RPCA) allows its fast approximate implementation based on a special form o a deep neural network with weights shared across all layers. However, empirically this fast approximation to RPCA fails to find representations that are parsemonious. We resolve these bad local minima by relaxing the elementwise L1 and L2 priors and instead utilize a structure inducing k-sparsity prior. In a discriminative classification task the newly learned representations outperform these from the original approximate RPCA formulation significantly.