eprintid: 4003
rev_number: 9
eprint_status: archive
userid: 17
dir: disk0/00/00/40/03
datestamp: 2020-07-10 05:41:39
lastmod: 2020-07-10 05:41:46
status_changed: 2020-07-10 05:41:46
type: conference_item
metadata_visibility: show
creators_name: Le Trung, Thanh
creators_name: Karim, Abed-Meraim
creators_name: Nguyen Linh, Trung
creators_name: Remy, Boyer
creators_id: letrungthanhtbt@gmail.com
creators_id: karim.abed-meraim@univ-orleans.fr
creators_id: linhtrung@vnu.edu.vn
creators_id: remy.boyer@univ-lille.fr
title: Adaptive Algorithms for Tracking Tensor-Train Decomposition of Streaming Tensors
ispublished: inpress
subjects: ECE
subjects: IT
divisions: avitech
divisions: fac_fet
abstract: Tensor-train (TT) decomposition has been an efficient tool to find low order approximation of large-scale, high-order tensors. Existing TT decomposition algorithms are either of high computational complexity or operating in batch-mode, hence quite inefficient for (near) real-time processing. In this paper, we propose a novel adaptive algorithm for TT decomposition of streaming tensors whose slices are serially acquired over time. By leveraging the alternating minimization framework, our estimator minimizes an exponentially weighted least-squares cost function in an efficient way. The proposed method can yield an estimation accuracy very close to the error bound. Numerical experiments show that the proposed algorithm is capable of adaptive TT decomposition with a competitive performance evaluation on both synthetic and real data.
date: 2021-01
contact_email: linhtrung@vnu.edu.vn
full_text_status: none
pres_type: paper
event_title: 28th European Signal Processing Conference (EUSIPCO)
event_location: Amsterdam, The Netherlands
event_dates: Jan 2021
event_type: conference
refereed: TRUE
citation:   Le Trung, Thanh and Karim, Abed-Meraim and Nguyen Linh, Trung and Remy, Boyer  (2021) Adaptive Algorithms for Tracking Tensor-Train Decomposition of Streaming Tensors.  In: 28th European Signal Processing Conference (EUSIPCO), Jan 2021, Amsterdam, The Netherlands.    (In Press)