Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Projected gradient methods for nonnegative matrix factorization.

Chih-Jen Lin1

  • 1Department of Computer Science, National Taiwan University, Taipei 106, Taiwan. cjlin@csie.ntu.edu.tw

Neural Computation
|August 25, 2007
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Rewiring the luteal microenvironment: hemodynamic and molecular insights into eCG-supported CL development in indigenous White Lamphun cattle.

Reproduction & fertility·2025
Same author

An Overview of Advancements in Proteomic Approaches to Enhance Livestock Production and Aquaculture.

Animals : an open access journal from MDPI·2025
Same author

Effect of eCG on Terminal Follicular Growth and Corpus Luteum Development and Blood Perfusion in Estrous-Synchronized White Lamphun Cattle.

Animals : an open access journal from MDPI·2025
Same author

Extracellular vesicles secreted by cumulus cells contain microRNAs that are potential regulatory factors of mouse oocyte developmental competence.

Molecular human reproduction·2024
Same author

One-Class SVM Probabilistic Outputs.

IEEE transactions on neural networks and learning systems·2024
Same author

Recent advances in the understanding of tubal ectopic pregnancy.

Faculty reviews·2023
Same journal

A Model-Free Reinforcement Learning Implementation of Decision Making Under Uncertainty by Sequential Sampling.

Neural computation·2026
Same journal

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning.

Neural computation·2026
Same journal

Hierarchical Active Inference Using Successor Representations.

Neural computation·2026
Same journal

W-Kernel and Its Principal Space for Frequentist Evaluation of Bayesian Estimators.

Neural computation·2026
Same journal

A Hidden Markov Model-Inspired Sequence Classification Method for Hyperdimensional Computing.

Neural computation·2026
Same journal

Sparse Graphical Modeling for Electrophysiological Phase-Based Connectivity Using Circular Statistics.

Neural computation·2026
See all related articles

This study introduces projected gradient methods for nonnegative matrix factorization (NMF), a type of bound-constrained optimization. One proposed NMF method shows faster convergence than existing approaches.

Area of Science:

  • Optimization methods
  • Numerical analysis
  • Machine learning

Background:

  • Nonnegative matrix factorization (NMF) is commonly solved as a minimization problem.
  • Bound-constrained optimization techniques are well-established but underexplored in NMF.

Purpose of the Study:

  • To apply projected gradient methods to nonnegative matrix factorization.
  • To develop efficient and effective optimization techniques for NMF.

Main Methods:

  • Proposed two novel projected gradient algorithms for NMF.
  • Analyzed the optimization properties and convergence of the proposed methods.
  • Compared performance against the standard multiplicative update approach.

Main Results:

Related Experiment Videos

  • The proposed projected gradient methods demonstrate strong optimization properties for NMF.
  • One method exhibits faster convergence compared to the multiplicative update algorithm.
  • Efficient implementation strategies were discussed and validated.

Conclusions:

  • Projected gradient methods offer a promising alternative for NMF optimization.
  • The developed NMF algorithms provide performance improvements over existing methods.
  • Accessible Matlab code is provided for practical application.