Accelerated Doubly Stochastic Gradient Descent for Tensor CP Decomposition

Qingsong Wang (), Chunfeng Cui () and Deren Han ()
Additional contact information
Qingsong Wang: Beihang University
Chunfeng Cui: Beihang University
Deren Han: Beihang University

Journal of Optimization Theory and Applications, 2023, vol. 197, issue 2, No 10, 665-704

Abstract: Abstract In this paper, we focus on the acceleration of doubly stochastic gradient descent method for computing the CANDECOMP/PARAFAC (CP) decomposition of tensors. This optimization problem has N blocks, where N is the order of the tensor. Under the doubly stochastic framework, each block subproblem is solved by the vanilla stochastic gradient method. However, the convergence analysis requires that the variance converges to zero, which is hard to check in practice and may not hold in some implementations. In this paper, we propose accelerating the stochastic gradient method by the momentum acceleration and the variance reduction technique, denoted as DS-MVR. Theoretically, the convergence of DS-MVR only requires the variance to be bounded. Under mild conditions, we show DS-MVR converges to a stochastic $$\varepsilon $$ ε -stationary solution in $$\tilde{\mathcal {O}}(N^{3/2}\varepsilon ^{-3})$$ O ~ ( N 3 / 2 ε - 3 ) iterations with varying stepsizes and in $$\mathcal {O}(N^{3/2}\varepsilon ^{-3})$$ O ( N 3 / 2 ε - 3 ) iterations with constant stepsizes, respectively. Numerical experiments on four real-world datasets show that our proposed algorithm can get better results compared with the baselines.

Keywords: Tensor CANDECOMP/PARAFAC decomposition; Doubly stochastic gradient descent; Nonconvex optimization; Variance reduction; Momentum acceleration; 15A72; 90C26; 90C30 (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10957-023-02193-5 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:joptap:v:197:y:2023:i:2:d:10.1007_s10957-023-02193-5

Ordering information: This journal article can be ordered from
http://www.springer. ... cs/journal/10957/PS2

DOI: 10.1007/s10957-023-02193-5

Access Statistics for this article

Journal of Optimization Theory and Applications is currently edited by Franco Giannessi and David G. Hull

More articles in Journal of Optimization Theory and Applications from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().