Work

Online and Differentially-Private Tensor Decomposition

Year: 2016

Type: preprint

Abstract: In this paper, we resolve many of the key algorithmic questions regarding robustness, memory efficiency, and differential privacy of tensor decomposition. We propose simple variants of the tensor power method which enjoy these strong properties. We present the first guarantees for online tensor power method which has a linear memory requirement. Moreover, we present a noise calibrated tensor power method with efficient privacy guarantees. At the heart of all these guarantees lies a careful perturbation analysis derived in this paper which improves up on the existing results significantly.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.1606.06237

Authors: Wang, Yining, Anandkumar, Animashree

Institution: Carnegie Mellon University

Language: English

Topic: Tensor decomposition and applications

Subfield: Computational Mathematics

Field: Mathematics

Domain: Physical Sciences

Open Access status: green

Funders: National Science Foundation, Office of Naval Research, Air Force Office of Scientific Research, Army Research Office

Awards: G1523888516, G2747436919, G6098521345, G6274897657, G7142813775, G7452299184, G8727049869, G8818057589, G8876996369, CAREER: Modeling Dependencies via Graphs: Scalable Inference Methods for Massive Datasets

OpenAlex ID: W2472385082

Cites:

Cited by: 25

Related to: 10