CaltechAUTHORS
  A Caltech Library Service

Online and Differentially-Private Tensor Decomposition

Wang, Yining and Anandkumar, Animashree (2016) Online and Differentially-Private Tensor Decomposition. In: Neural Information Processing Systems 2016. Neural Information Processing Systems Foundation , La Jolla, CA, Art. No. 6498. ISBN 9781510838819. http://resolver.caltech.edu/CaltechAUTHORS:20190401-123322786

[img] PDF - Published Version
See Usage Policy.

355Kb
[img] Archive (ZIP) - Supplemental Material
See Usage Policy.

875Kb

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20190401-123322786

Abstract

Tensor decomposition is positioned to be a pervasive tool in the era of big data. 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 propose the first streaming method with 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.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
https://papers.nips.cc/paper/6498-online-and-differentially-private-tensor-decompositionPublisherArticle
http://arxiv.org/abs/1606.06237arXivArticle
Additional Information:A. Anandkumar is supported in part by Microsoft Faculty Fellowship, NSF Career award CCF-1254106, ONR Award N00014- 14-1-0665, ARO YIP Award W911NF-13-1-0084 and AFOSR YIP FA9550-15-1-0221.
Funders:
Funding AgencyGrant Number
Microsoft Faculty FellowshipUNSPECIFIED
NSFCCF-1254106
Office of Naval Research (ONR)N00014-14-1-0665
Army Research Office (ARO)W911NF-13-1-0084
Air Force Office of Scientific Research (AFOSR)FA9550-15-1-0221
Subject Keywords:Tensor decomposition, tensor power method, online methods, streaming, differential privacy, perturbation analysis
Record Number:CaltechAUTHORS:20190401-123322786
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:20190401-123322786
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:94327
Collection:CaltechAUTHORS
Deposited By: George Porter
Deposited On:01 Apr 2019 22:04
Last Modified:01 Apr 2019 22:04

Repository Staff Only: item control page