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

Learning Rates for Classification with Gaussian Kernels.

Shao-Bo Lin1, Jinshan Zeng2, Xiangyu Chang3

  • 1Department of Statistics, Wenzhou University, Wenzhou 325035, China sblin1983@gmail.com.

Neural Computation
|April 15, 2017
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

Hourly Exposure to Ambient Air Pollutants and Risk of Acute Aortic Dissection: Evidence From 162 Chinese Cities.

Journal of occupational and environmental medicine·2025
Same author

B7-H3-mediated reversal of CAR-T cell exhaustion induces a notable antitumour response in ovarian cancer models.

EBioMedicine·2025
Same author

Brain rewired: Redox control of brain cell crosstalk via nanotubes and vesicles.

Free radical biology & medicine·2025
Same author

Learned low-rank representation and its theoretical convergence analysis.

Neural networks : the official journal of the International Neural Network Society·2025
Same author

OTUD1 inhibits endometriosis fibrosis by deubiquitinating MADH7.

Molecular human reproduction·2025
Same author

Detection of green pepper impurities based on hyperspectral imaging technology.

Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy·2025
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

Support Vector Machines (SVM) with Gaussian kernels achieve near-optimal learning rates for binary classification tasks with smooth regression functions. Under Tsybakov noise conditions, infinitely smooth functions yield improved learning rates with SVMs.

Area of Science:

  • Machine Learning
  • Computational Statistics
  • Pattern Recognition

Background:

  • Binary classification is a fundamental machine learning task.
  • Support Vector Machines (SVM) with Gaussian kernels are widely used for classification.
  • Error analysis is crucial for understanding classifier performance.

Purpose of the Study:

  • To perform a refined error analysis for binary classification using SVM with Gaussian kernels and convex loss.
  • To investigate the impact of different loss functions and noise conditions on SVM performance.

Main Methods:

  • Utilizing Support Vector Machines (SVM) with a Gaussian kernel.
  • Analyzing performance with various convex loss functions, including truncated quadratic and quadratic loss.
  • Applying Tsybakov noise assumptions to assess performance under noisy data.

Related Experiment Videos

Main Results:

  • SVM with Gaussian kernel achieves near-optimal learning rates for smooth regression functions with specific loss functions.
  • Under Tsybakov noise and infinite smoothness, SVM achieves a learning rate of order [Formula: see text].

Conclusions:

  • The study provides theoretical guarantees for SVM performance in binary classification.
  • Refined error analysis demonstrates the effectiveness of SVM with Gaussian kernels under various conditions.