A quadratically convergent proximal algorithm for nonnegative tensor decomposition
Abstract
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. If the algorithm converges to the global optimum, we show that -quadratic convergence can be obtained in the exact case. Global convergence is achieved via backtracking on the forward-backward envelope function. The -quadratic convergence is verified experimentally, and we illustrate that using the GN step significantly reduces number of (expensive) gradient computations compared to proximal gradient descent.
Cite
@article{arxiv.2003.03502,
title = {A quadratically convergent proximal algorithm for nonnegative tensor decomposition},
author = {Nico Vervliet and Andreas Themelis and Panagiotis Patrinos and Lieven De Lathauwer},
journal= {arXiv preprint arXiv:2003.03502},
year = {2024}
}