Počet záznamů: 1
Tensor Networks for Latent Variable Analysis: Novel Algorithms for Tensor Train Approximation
- 1.
SYSNO ASEP 0518308 Druh ASEP J - Článek v odborném periodiku Zařazení RIV J - Článek v odborném periodiku Poddruh J Článek ve WOS Název Tensor Networks for Latent Variable Analysis: Novel Algorithms for Tensor Train Approximation Tvůrce(i) Phan, A. H. (RU)
Cichocki, A. (RU)
Uschmajew, A. (DE)
Tichavský, Petr (UTIA-B) RID, ORCID
Luta, G. (US)Celkový počet autorů 6 Zdroj.dok. IEEE Transactions on Neural Networks and Learning Systems - ISSN 2162-237X
Roč. 31, č. 11 (2020), s. 4622-4636Poč.str. 17 s. Forma vydání Tištěná - P Jazyk dok. eng - angličtina Země vyd. US - Spojené státy americké Klíč. slova Blind source separation ; tensor network (TN) ; image denoising ; nested Tucker ; tensor train (TT) decomposition ; Tucker-2 (TK2) decomposition ; truncated singular value decomposition (SVD) Vědní obor RIV BB - Aplikovaná statistika, operační výzkum Obor OECD Electrical and electronic engineering CEP GA17-00902S GA ČR - Grantová agentura ČR Způsob publikování Omezený přístup Institucionální podpora UTIA-B - RVO:67985556 UT WOS 000587699700017 EID SCOPUS 85093097685 DOI https://doi.org/10.1109/TNNLS.2019.2956926 Anotace Decompositions of tensors into factor matrices, which interact through a core tensor, have found numerous applications in signal processing and machine learning. A more general tensor model that represents data as an ordered network of subtensors of order-2 or order-3 has, so far, not been widely considered in these fields, although this so-called tensor network (TN) decomposition has been long studied in quantum physics and scientific computing. In this article, we present novel algorithms and applications of TN decompositions, with a particular focus on the tensor train (TT) decomposition and its variants. The novel algorithms developed for the TT decomposition update, in an alternating way, one or several core tensors at each iteration and exhibit enhanced mathematical tractability and scalability for large-scale data tensors. For rigor, the cases of the given ranks, given approximation error, and the given error bound are all considered. The proposed algorithms provide well-balanced TT-decompositions and are tested in the classic paradigms of blind source separation from a single mixture, denoising, and feature extraction, achieving superior performance over the widely used truncated algorithms for TT decomposition. Pracoviště Ústav teorie informace a automatizace Kontakt Markéta Votavová, votavova@utia.cas.cz, Tel.: 266 052 201. Rok sběru 2021 Elektronická adresa https://ieeexplore.ieee.org/document/8984730
Počet záznamů: 1