An end-to-end Differentially Private Latent Dirichlet Allocation Using a Spectral Algorithm

Chris Decarolis, Mukul Ram, Seyed Esmaeili, Yu-Xiang Wang, Furong Huang

Abstract: We provide an end-to-end differentially private spectral algorithm for learning LDA, based on matrix/tensor decompositions, and establish theoretical guarantees on utility/consistency of the estima...