Tensor decomposition via joint matrix schur decomposition. / Colombo, Nicolo; Vlassis, Nikos.

ICML'16 Proceedings of the 33rd International Conference on International Conference on Machine Learning. ed. / Kilian Q. Weinberger; Maria Florina Balcan. International Machine Learning Society (IMLS), 2016. p. 2820-2828 (33rd International Conference on Machine Learning, ICML 2016; Vol. 48).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Published

Links

Abstract

We describe an approach to tensor decomposition that involves extracting a set of observable matrices from the tensor and applying an approximate joint Schur decomposition on those matrices, and wc establish the corresponding first-order perturbation bounds. We develop a novel iterative Gauss-Newton algorithm for joint matrix Schur decomposition, which minimizes a nonconvex objective over the manifold of orthogonal matrices, and which is guaranteed to con-verge to a global optimum under certain conditions. We empirically demonstrate that our algorithm is faster and at least as accurate and robust than state-of-the-art algorithms for this problem.

Original languageEnglish
Title of host publicationICML'16 Proceedings of the 33rd International Conference on International Conference on Machine Learning
EditorsKilian Q. Weinberger, Maria Florina Balcan
PublisherInternational Machine Learning Society (IMLS)
Pages2820-2828
Number of pages9
ISBN (Electronic)9781510829008
Publication statusPublished - 19 Jun 2016
Event33rd International Conference on Machine Learning, ICML 2016 - New York City, United States
Duration: 19 Jun 201624 Jun 2016

Publication series

Name33rd International Conference on Machine Learning, ICML 2016
Volume48

Conference

Conference33rd International Conference on Machine Learning, ICML 2016
CountryUnited States
CityNew York City
Period19/06/1624/06/16
This open access research output is licenced under a Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported License.

ID: 34305272