Accelerated Multiplicative Updates and Hierarchical ALS Algorithms for Nonnegative Matrix Factorization

Details Accelerated Multiplicative Updates and Hierarchical ALS Algorithms for Nonnegative Matrix Factorization Accelerated Multiplicative Updates and Hierarchical ALS Algorithms for Nonnegative Matrix Factorization

2011-07-26

arxiv.org/abs/1107.5194v2

Mathematics

Optimization and Control

17 pages, 10 figures. New Section 4 about the convergence of the accelerated algorithms; Removed Section 5 about efficiency of

Scientific paper

Nonnegative matrix factorization (NMF) is a data analysis technique used in a great variety of applications such as text mining, image processing, hyperspectral data analysis, computational biology, and clustering. In this paper, we consider two well-known algorithms designed to solve NMF problems, namely the multiplicative updates of Lee and Seung and the hierarchical alternating least squares of Cichocki et al. We propose a simple way to significantly accelerate these schemes, based on a careful analysis of the computational cost needed at each iteration, while preserving their convergence properties. This acceleration technique can also be applied to other algorithms, which we illustrate on the projected gradient method of Lin. The efficiency of the accelerated algorithms is empirically demonstrated on image and text datasets, and compares favorably with a state-of-the-art alternating nonnegative least squares algorithm.

Affiliated with

Also associated with

No associations

Rating

Accelerated Multiplicative Updates and Hierarchical ALS Algorithms for Nonnegative Matrix Factorization does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Accelerated Multiplicative Updates and Hierarchical ALS Algorithms for Nonnegative Matrix Factorization, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Accelerated Multiplicative Updates and Hierarchical ALS Algorithms for Nonnegative Matrix Factorization will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-93541