A quadratically convergent proximal algorithm for nonnegative tensor decomposition

Nico Vervliet, Andreas Themelis, Panagiotis Patrinos, Lieven de Lathauwer

研究成果: Chapter in Book/Report/Conference proceedingConference contribution

抄録

The decomposition of tensors into simple rank-1 terms is key in a variety of applications in signal processing, data analysis and machine learning. While this canonical polyadic decomposition (CPD) is unique under mild conditions, including prior knowledge such as nonnegativity can facilitate interpretation of the components. Inspired by the effectiveness and efficiency of Gauss-Newton (GN) for unconstrained CPD, we derive a proximal, semismooth GN type algorithm for nonnegative tensor factorization. Global convergence to local minima is achieved via backtracking on the forward-backward envelope function. If the algorithm converges to a global optimum, we show that Q-quadratic rates are obtained in the exact case. Such fast rates are verified experimentally, and we illustrate that using the GN step significantly reduces number of (expensive) gradient computations compared to proximal gradient descent.

本文言語英語
ホスト出版物のタイトル28th European Signal Processing Conference, EUSIPCO 2020 - Proceedings
出版社European Signal Processing Conference, EUSIPCO
ページ1020-1024
ページ数5
ISBN(電子版)9789082797053
DOI
出版ステータス出版済み - 1 24 2021
外部発表はい
イベント28th European Signal Processing Conference, EUSIPCO 2020 - Amsterdam, オランダ
継続期間: 8 24 20208 28 2020

出版物シリーズ

名前European Signal Processing Conference
2021-January
ISSN(印刷版)2219-5491

会議

会議28th European Signal Processing Conference, EUSIPCO 2020
国/地域オランダ
CityAmsterdam
Period8/24/208/28/20

All Science Journal Classification (ASJC) codes

  • 信号処理
  • 電子工学および電気工学

フィンガープリント

「A quadratically convergent proximal algorithm for nonnegative tensor decomposition」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル