Non-asymptotic Excess Risk Bounds for Classification with Deep Convolutional Neural Networks

Abstract

In this paper, we consider the problem of binary classification with a class of general deep convolutional neural networks, which includes fully-connected neural networks and fully convolutional neural networks as special cases. We establish non-asymptotic excess risk bounds for a class of convex surrogate losses and target functions with different modulus of continuity. An important feature of our results is that we clearly define the prefactors of the risk bounds in terms of the input data dimension and other model parameters and show that they depend polynomially on the dimensionality in some important models. We also show that the classification methods with CNNs can circumvent the curse of dimensionality if the input data is supported on an approximate low-dimensional manifold. To establish these results, we derive an upper bound for the covering number for the class of general convolutional neural networks with a bias term in each convolutional layer, and derive new results on the approximation power of CNNs for any uniformly-continuous target functions. These results provide further insights into the complexity and the approximation power of general convolutional neural networks, which are of independent interest and may have other applications. Finally, we apply our general results to analyze the non-asymptotic excess risk bounds for four widely used methods with different loss functions using CNNs, including the least squares, the logistic, the exponential and the SVM hinge losses.

arXiv commentGuohao Shen and Yuling Jiao contributed equally to this work. Co-corresponding authors: Yuanyuan Lin (Email: [email protected]) and Jian Huang (Email: [email protected])

References in corpus (14)

• Deep Learning in Neural Networks: An Overview
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Fast learning rates for plug-in classifiers
• Risk bounds for statistical learning
• Spectrally-normalized margin bounds for neural networks
• Optimal approximation of continuous functions by very deep ReLU networks
• The Expressive Power of Neural Networks: A View from the Width
• Nonlinear Approximation via Compositions
• Deep ReLU network approximation of functions on a manifold
• Approximation and Non-parametric Estimation of ResNet-type Convolutional Neural Networks
• Understanding Generalization and Optimization Performance of Deep CNNs
• Generalization Bounds for Convolutional Neural Networks
• Deep Nonparametric Regression on Approximate Manifolds: Non-Asymptotic Error Bounds with Polynomial Prefactors
• Convex Risk Minimization and Conditional Probability Estimation