Fast convergence rates of deep neural networks for classification. (June 2021)

• Record Type: Journal Article
• Authors: Kim, Yongdai; Ohn, Ilsang; Kim, Dongha
• Is Part Of: Neural networks. Volume 138(2021)
• Page Start: 179
• Page End: 197
• Publication Date: 2021-06
• Subjects: Classification -- Deep neural network -- Excess risk -- Fast convergence rate; Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2021.02.012
• Languages: English
• ISSNs: 0893-6080

Abstract

Abstract: We derive the fast convergence rates of a deep neural network (DNN) classifier with the rectified linear unit (ReLU) activation function learned using the hinge loss. We consider three cases for a true model: (1) a smooth decision boundary, (2) smooth conditional class probability, and (3) the margin condition (i.e., the probability of inputs near the decision boundary is small). We show that the DNN classifier learned using the hinge loss achieves fast rate convergences for all three cases provided that the architecture (i.e., the number of layers, number of nodes and sparsity) is carefully selected. An important implication is that DNN architectures are very flexible for use in various cases without much modification. In addition, we consider a DNN classifier learned by minimizing the cross-entropy, and show that the DNN classifier achieves a fast convergence rate under the conditions that the noise exponent and margin exponent are large. Even though they are strong, we explain that these two conditions are not too absurd for image classification problems. To confirm our theoretical explanation, we present the results of a small numerical study conducted to compare the hinge loss and cross-entropy.