Accelerating block coordinate descent for nonnegative tensor factorization. Issue 5 (16th March 2021)

• Record Type: Journal Article
• Authors: Man Shun Ang, Andersen; Cohen, Jeremy E.; Gillis, Nicolas; Thi Khanh Hien, Le
• Is Part Of: Numerical linear algebra with applications. Volume 28:Issue 5(2021)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2021-03-16
• Subjects: block‐coordinate descent -- Nesterov extrapolation -- nonconvex optimization -- nonnegative tensor factorization; Algebras, Linear -- Periodicals; 512.5
• DOI: 10.1002/nla.2373
• Languages: English
• ISSNs: 1070-5325

Abstract

Abstract: This paper is concerned with improving the empirical convergence speed of block‐coordinate descent algorithms for approximate nonnegative tensor factorization (NTF). We propose an extrapolation strategy in‐between block updates, referred to as heuristic extrapolation with restarts (HER). HER significantly accelerates the empirical convergence speed of most existing block‐coordinate algorithms for NTF, in particular for challenging computational scenarios, while requiring a negligible additional computational budget.