Convergence rates of deep ReLU networks for multiclass classification

DOI10.1214/22-EJS2011zbMath1493.62156arXiv2108.00969OpenAlexW3192475660MaRDI QIDQ2137813

Thijs Bos, Johannes Schmidt-Hieber

Publication date: 11 May 2022

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2108.00969

zbMATH Keywords

convergence ratesmulticlass classificationmargin conditionconditional class probabilitiesReLU networks

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Nonparametric estimation (62G05) Artificial neural networks and deep learning (68T07)

Related Items

Adaptive novelty detection with false discovery rate guarantee, Optimal convergence rates of deep neural networks in a classification setting, Multiclass classification for multidimensional functional data through deep neural networks, Analysis of convolutional neural network image classifiers in a hierarchical max-pooling model with additional local pooling

Uses Software

• UCI-ml
• ElemStatLearn
• ImageNet
• AlexNet

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• On maximum likelihood estimation in infinite dimensional parameter spaces
• Fast learning rates for plug-in classifiers
• Minimum contrast estimators on sieves: Exponential bounds and rates of convergence
• Inequalities for quasiconformal mappings in space
• Mutual information, metric entropy and cumulative relative entropy risk
• Information-theoretic determination of minimax rates of convergence
• Smooth discrimination analysis
• Optimal aggregation of classifiers in statistical learning.
• Probability inequalities for likelihood ratios and convergence rates of sieve MLEs
• Weak convergence and empirical processes. With applications to statistics
• On the rate of convergence of fully connected deep neural network regression estimates
• Nonparametric regression using deep neural networks with ReLU activation function
• Error bounds for approximations with deep ReLU networks
• On deep learning as a remedy for the curse of dimensionality in nonparametric regression
• Rate-optimal estimation for a general class of nonparametric regression models with unknown link functions
• Rényi Divergence and Kullback-Leibler Divergence
• Probability Inequalities for the Sum of Independent Random Variables
• Nonparametric Regression Based on Hierarchical Interaction Models
• Convexity, Classification, and Risk Bounds
• Fast convergence rates of deep neural networks for classification