An error analysis for deep binary classification with sigmoid loss

DOI10.1016/J.INS.2024.121166MaRDI QIDQ6588360zbMATH OpenFDO

Authors Changshi Li, Yu Ling Jiao, Jerry Zhijian Yang

Publication date 15 August 2024

Published in Information Sciences (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.INS.2024.121166

zbMATH Keywords

binary classificationconvergence rateexcess riskdeep neural networksoutlier noisessigmoid loss

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Recommendations

• Fast generalization error bound of deep learning without scale invariance of activation functions
• Power function error initialization can improve convergence of backpropagation learning in neural networks for classification
• A novel multi-scale loss function for classification problems in machine learning
• Levenberg-Marquardt multi-classification using hinge loss function
• Fast convergence rates of deep neural networks for classification

Cites work

• scientific article; zbMATH DE number 1420699 (Why is no real title available?)
• scientific article; zbMATH DE number 7306873 (Why is no real title available?)
• scientific article; zbMATH DE number 7064043 (Why is no real title available?)
• Boosting in the presence of outliers: adaptive classification with nonconvex loss functions
• Convexity, Classification, and Risk Bounds
• Deep neural networks for estimation and inference
• Deep neural networks for rotation-invariance approximation and learning
• Fast convergence rates of deep neural networks for classification
• Fast learning rates for plug-in classifiers
• Fully corrective gradient boosting with squared hinge: fast learning rates and early stopping
• How to compare different loss functions and their risks
• Local Rademacher complexities
• Mathematical Foundations of Infinite-Dimensional Statistical Models
• Neural Network Learning
• On deep learning as a remedy for the curse of dimensionality in nonparametric regression
• On the rate of convergence of fully connected deep neural network regression estimates
• Robust Truncated Hinge Loss Support Vector Machines
• Statistical behavior and consistency of classification methods based on convex risk minimization.
• Support Vector Machines
• Weak convergence and empirical processes. With applications to statistics

This page was built for publication: An error analysis for deep binary classification with sigmoid loss

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6588360)