A Momentum Accelerated Algorithm for ReLU-based Nonlinear Matrix Decomposition

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Qingsong, Cui, Chunfeng, Han, Deren
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913521509335040
author Wang, Qingsong
Cui, Chunfeng
Han, Deren
author_facet Wang, Qingsong
Cui, Chunfeng
Han, Deren
contents Recently, there has been a growing interest in the exploration of Nonlinear Matrix Decomposition (NMD) due to its close ties with neural networks. NMD aims to find a low-rank matrix from a sparse nonnegative matrix with a per-element nonlinear function. A typical choice is the Rectified Linear Unit (ReLU) activation function. To address over-fitting in the existing ReLU-based NMD model (ReLU-NMD), we propose a Tikhonov regularized ReLU-NMD model, referred to as ReLU-NMD-T. Subsequently, we introduce a momentum accelerated algorithm for handling the ReLU-NMD-T model. A distinctive feature, setting our work apart from most existing studies, is the incorporation of both positive and negative momentum parameters in our algorithm. Our numerical experiments on real-world datasets show the effectiveness of the proposed model and algorithm. Moreover, the code is available at https://github.com/nothing2wang/NMD-TM.
format Preprint
id arxiv_https___arxiv_org_abs_2402_02442
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Momentum Accelerated Algorithm for ReLU-based Nonlinear Matrix Decomposition
Wang, Qingsong
Cui, Chunfeng
Han, Deren
Machine Learning
Image and Video Processing
Recently, there has been a growing interest in the exploration of Nonlinear Matrix Decomposition (NMD) due to its close ties with neural networks. NMD aims to find a low-rank matrix from a sparse nonnegative matrix with a per-element nonlinear function. A typical choice is the Rectified Linear Unit (ReLU) activation function. To address over-fitting in the existing ReLU-based NMD model (ReLU-NMD), we propose a Tikhonov regularized ReLU-NMD model, referred to as ReLU-NMD-T. Subsequently, we introduce a momentum accelerated algorithm for handling the ReLU-NMD-T model. A distinctive feature, setting our work apart from most existing studies, is the incorporation of both positive and negative momentum parameters in our algorithm. Our numerical experiments on real-world datasets show the effectiveness of the proposed model and algorithm. Moreover, the code is available at https://github.com/nothing2wang/NMD-TM.
title A Momentum Accelerated Algorithm for ReLU-based Nonlinear Matrix Decomposition
topic Machine Learning
Image and Video Processing
url https://arxiv.org/abs/2402.02442