A note on margin-based loss functions in classification

DOI10.1016/j.spl.2004.03.002zbMath1058.62052OpenAlexW2022465039MaRDI QIDQ1770065

Yi Lin

Publication date: 7 April 2005

Published in: Statistics \& Probability Letters (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.spl.2004.03.002

zbMATH Keywords

MarginFisher consistencyBayes rule of classificationMethod of regularizationMethod of sieves

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Bayesian inference (62F15)

Related Items (26)

Deep learning: a statistical viewpoint ⋮ Angle-based cost-sensitive multicategory classification ⋮ The new interpretation of support vector machines on statistical learning theory ⋮ Directed Community Detection With Network Embedding ⋮ Robust logistic regression with shift parameter estimation ⋮ A simple extension of boosting for asymmetric mislabeled data ⋮ Estimating heterogeneous treatment effects versus building individualized treatment rules: connection and disconnection ⋮ Data-adaptive discriminative feature localization with statistically guaranteed interpretation ⋮ Efficient homomorphic comparison methods with optimal complexity ⋮ Oracle properties of SCAD-penalized support vector machine ⋮ A robust classification framework with mixture correntropy ⋮ Robust Support Vector Machines for Classification with Nonconvex and Smooth Losses ⋮ Does modeling lead to more accurate classification? A study of relative efficiency in linear classification ⋮ Quadratic Majorization for Nonconvex Loss with Applications to the Boosting Algorithm ⋮ Robust boosting with truncated loss functions ⋮ Unnamed Item ⋮ A Bayes Empirical Bayes Decision Rule for Classification ⋮ Bayes Empirical Bayes Classification of Components Using Masked Data ⋮ Deformation of log-likelihood loss function for multiclass boosting ⋮ New multicategory boosting algorithms based on multicategory Fisher-consistent losses ⋮ Comment ⋮ Theory of Classification: a Survey of Some Recent Advances ⋮ Robust penalized logistic regression with truncated loss functions ⋮ Convergence rates of generalization errors for margin-based classification ⋮ Another Look at Distance-Weighted Discrimination ⋮ On the Effect and Remedies of Shrinkage on Classification Probability Estimation

Uses Software

• ElemStatLearn
• SSVM

Cites Work

• Unnamed Item
• Unnamed Item
• Convergence rate of sieve estimates
• Improved generalization through explicit optimization of margins
• Arcing classifiers. (With discussion)
• Regression analysis under link violation
• Empirical margin distributions and bounding the generalization error of combined classifiers
• Statistical behavior and consistency of classification methods based on convex risk minimization.
• Boosting a weak learning algorithm by majority
• Support-vector networks
• Asymptotic analysis of penalized likelihood and related estimators
• Efficient agnostic learning of neural networks with bounded fan-in
• On ψ-Learning
• Convexity, Classification, and Risk Bounds
• Prediction Games and Arcing Algorithms
• The elements of statistical learning. Data mining, inference, and prediction

This page was built for publication: A note on margin-based loss functions in classification