2000 character limit reached
A Bias Trick for Centered Robust Principal Component Analysis
Published 19 Nov 2019 in cs.LG and stat.ML | (1911.08024v1)
Abstract: Outlier based Robust Principal Component Analysis (RPCA) requires centering of the non-outliers. We show a "bias trick" that automatically centers these non-outliers. Using this bias trick we obtain the first RPCA algorithm that is optimal with respect to centering.
Paper Prompts
Sign up for free to create and run prompts on this paper.