Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

Parallel algorithms for large scale constrained tensor decomposition

Liavas Athanasios, Sidiropoulos Nikos

Simple record

URIhttp://purl.tuc.gr/dl/dias/A9192D3C-8477-4DC8-AE63-1C68B0B3D5FB-
Identifierhttps://doi.org/10.1109/ICASSP.2015.7178413-
Languageen-
TitleParallel algorithms for large scale constrained tensor decompositionen
CreatorLiavas Athanasiosen
CreatorΛιαβας Αθανασιοςel
CreatorSidiropoulos Nikosen
CreatorΣιδηροπουλος Νικολαοςel
Content SummaryMost tensor decomposition algorithms were developed for in-memory computation on a single machine. There are a few recent exceptions that were designed for parallel and distributed computation, but these cannot easily incorporate practically important constraints, such as nonnegativity. A new constrained tensor factorization framework is proposed in this paper, building upon the Alternating Direction method of Multipliers (ADMoM). It is shown that this simplifies computations, bypassing the need to solve constrained optimization problems in each iteration, yielding algorithms that are naturally amenable to parallel implementation. The methodology is exemplified using nonnegativity as a baseline constraint, but the proposed framework can incorporate many other types of constraints. Numerical experiments are encouraging, indicating that ADMoM-based nonnegative tensor factorization (NTF) has high potential as an alternative to state-of-the-art approaches.en
Type of ItemΠλήρης Δημοσίευση σε Συνέδριοel
Type of ItemConference Full Paperen
Licensehttp://creativecommons.org/licenses/by-nc-nd/4.0/en
Date of Item2015-11-17-
Date of Publication2015-
Bibliographic CitationA.P. Liavas, N.D. Sidiropoulos, "Parallel algorithms for large scale constrained tensor decomposition," in 2015 Acoustics, Speech and Signal Processing , IEEE International Conference on(ICASSP), doi: 10.1109/ICASSP.2015.7178413en

Services

Statistics

 

Copyright © DIAS 2013