Nonparametric Regression with Shallow Overparameterized Neural Networks Trained by GD with Early Stopping

Abstract

We explore the ability of overparameterized shallow neural networks to learn Lipschitz regression functions with and without label noise when trained by Gradient Descent (GD). To avoid the problem that in the presence of noisy labels, neural networks trained to nearly zero training error are inconsistent on this class, we propose an early stopping rule that allows us to show optimal rates. This provides an alternative to the result of Hu et al. (2021) who studied the performance of $\ell 2$ -regularized GD for training shallow networks in nonparametric regression which fully relied on the infinite-width network (Neural Tangent Kernel (NTK)) approximation. Here we present a simpler analysis which is based on a partitioning argument of the input space (as in the case of 1-nearest-neighbor rule) coupled with the fact that trained neural networks are smooth with respect to their inputs when trained by GD. In the noise-free case the proof does not rely on any kernelization and can be regarded as a finite-width result. In the case of label noise, by slightly modifying the proof, the noise is controlled using a technique of Yao, Rosasco, and Caponnetto (2007).

arXiv commentThe report contains a critical issue. For details see the note: http://proceedings.mlr.press/v134/kuzborskij21a/kuzborskij21a.pdf

References in corpus (10)

• Neural Tangent Kernel: Convergence and Generalization in Neural Networks
• A Convergence Theory for Deep Learning via Over-Parameterization
• Early stopping and non-parametric regression: An optimal data-dependent stopping rule
• Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks
• Polylogarithmic width suffices for gradient descent to achieve arbitrarily small test error with shallow ReLU networks
• Simultaneous Model Selection and Optimization through Parameter-free Stochastic Learning
• Regularization Matters: A Nonparametric Perspective on Overparametrized Neural Network
• Over-parametrized deep neural networks do not generalize well
• Empirical Risk Minimization in the Interpolating Regime with Application to Neural Network Learning
• Analysis of the rate of convergence of neural network regression estimates which are easy to implement