An error analysis for deep binary classification with sigmoid loss

DOI10.1016/j.ins.2024.121166MaRDI QIDQ6588360

Changshi Li, Jerry Zhijian Yang, Yu Ling Jiao

Publication date: 15 August 2024

Published in: Information Sciences (Search for Journal in Brave)

zbMATH Keywords

convergence ratebinary classificationexcess riskdeep neural networksoutlier noisessigmoid loss

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Fast learning rates for plug-in classifiers
• Statistical behavior and consistency of classification methods based on convex risk minimization.
• Weak convergence and empirical processes. With applications to statistics
• On the rate of convergence of fully connected deep neural network regression estimates
• On deep learning as a remedy for the curse of dimensionality in nonparametric regression
• Local Rademacher complexities
• How to compare different loss functions and their risks
• Support Vector Machines
• Robust Truncated Hinge Loss Support Vector Machines
• Neural Network Learning
• Boosting in the Presence of Outliers: Adaptive Classification With Nonconvex Loss Functions
• Mathematical Foundations of Infinite-Dimensional Statistical Models
• Deep Neural Networks for Estimation and Inference
• Deep neural networks for rotation-invariance approximation and learning
• Convexity, Classification, and Risk Bounds
• Fully corrective gradient boosting with squared hinge: fast learning rates and early stopping
• Fast convergence rates of deep neural networks for classification

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