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

The generalized LASSO.

Volker Roth1

  • 1Department of Computer Science III, University of Bonn, D-53117 Bonn, Germany. roth@cs.uni-bonn.de

IEEE Transactions on Neural Networks
|September 25, 2004
PubMed
Summary
This summary is machine-generated.

Generalized LASSO regression offers a probabilistic kernel regression alternative to Support Vector Machines (SVMs). This method overcomes SVM limitations, providing sparse solutions and handling outliers for large-scale machine learning problems.

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

Neural Dynamics of Social Cognition: A Single-Trial Computational Analysis of Learning Under Uncertainty.

Human brain mapping·2026
Same author

Machine Learning-Based Prediction of Short-Term Mortality After Coronary Artery Bypass Grafting: A Retrospective Cohort Study.

Biomedicines·2025
Same author

Localizing hierarchical prediction errors and precisions during an oddball task with volatility: Computational insights and relationship with psychosocial functioning in healthy individuals.

Imaging neuroscience (Cambridge, Mass.)·2025
Same author

Altered Perception of Environmental Volatility During Social Learning in Emerging Psychosis.

Computational psychiatry (Cambridge, Mass.)·2024
Same author

Machine Learning Facial Emotion Classifiers in Psychotherapy Research: A Proof-of-Concept Study.

Psychopathology·2023
Same author

Using Machine Learning-Based Algorithms to Identify and Quantify Exercise Limitations in Clinical Practice: Are We There Yet?

Medicine and science in sports and exercise·2023
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

Area of Science:

  • Machine Learning
  • Statistical Modeling
  • Computational Statistics

Background:

  • Support Vector Machines (SVMs) have gained traction in kernel regression but present limitations.
  • These limitations include a lack of probabilistic outputs, restricted kernel usage (Mercer kernels), and scalability issues due to increasing support vectors.
  • Existing methods struggle with noisy datasets and achieving highly sparse solutions.

Purpose of the Study:

  • To introduce a novel kernel regression technique that addresses the drawbacks of SVMs.
  • To present generalized LASSO regression as a robust and efficient alternative.
  • To demonstrate its capability in handling large-scale, outlier-corrupted datasets and producing sparse solutions.

Main Methods:

  • Development of generalized LASSO regression, a new class of kernel regressors.

Related Experiment Videos

  • Formulation of regression functionals solvable via iteratively reweighted least-squares (IRLS).
  • Design of an efficient algorithm with guaranteed global convergence for IRLS problems.

    • Main Results:

    • Generalized LASSO regression provides probabilistic outputs and handles outliers effectively.
    • The method achieves extremely sparse solutions, outperforming related approaches on benchmark datasets.
    • It offers a unified framework for various sparse regression models within the IRLS class.

    Conclusions:

    • Generalized LASSO regression is a powerful and versatile kernel regression method.
    • It surpasses SVMs in key areas like probabilistic interpretation, robustness, and solution sparsity.
    • The proposed algorithm efficiently solves a broad range of sparse regression problems.