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

arXiv: https://arxiv.org/abs/2107.05341 · HTML: https://mlsanity.com/paper/2107.05341/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 43 references that are in the map.
- First posted on arXiv 12 Jul 2021.

## Builds on (most cited first, 20 of 20)

- [Neural Tangent Kernel: Convergence and Generalization in Neural Networks](https://mlsanity.com/paper/1806.07572/) (2018)
- [A Convergence Theory for Deep Learning via Over-Parameterization](https://mlsanity.com/paper/1811.03962/) (2018)
- [Gradient Descent Provably Optimizes Over-parameterized Neural Networks](https://mlsanity.com/paper/1810.02054/) (2018)
- [Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks](https://mlsanity.com/paper/1901.08584/) (2019)
- [Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Lojasiewicz Condition](https://mlsanity.com/paper/1608.04636/) (2016)
- [Nonparametric regression using deep neural networks with ReLU activation function](https://mlsanity.com/paper/1708.06633/) (2017)
- [Breaking the Curse of Dimensionality with Convex Neural Networks](https://mlsanity.com/paper/1412.8690/) (2014)
- [Size-Independent Sample Complexity of Neural Networks](https://mlsanity.com/paper/1712.06541/) (2017)
- [Deep learning: a statistical viewpoint](https://mlsanity.com/paper/2103.09177/) (2021)
- [Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks](https://mlsanity.com/paper/1905.13210/) (2019)
- [On the Inductive Bias of Neural Tangent Kernels](https://mlsanity.com/paper/1905.12173/) (2019)
- [Towards moderate overparameterization: global convergence guarantees for training shallow neural networks](https://mlsanity.com/paper/1902.04674/) (2019)
- [Polylogarithmic width suffices for gradient descent to achieve arbitrarily small test error with shallow ReLU networks](https://mlsanity.com/paper/1909.12292/) (2019)
- [Does data interpolation contradict statistical optimality?](https://mlsanity.com/paper/1806.09471/) (2018)
- [Early stopping and non-parametric regression: An optimal data-dependent stopping rule](https://mlsanity.com/paper/1306.3574/) (2013)
- [A Continuous-Time View of Early Stopping for Least Squares](https://mlsanity.com/paper/1810.10082/) (2018)
- [Consistency of Interpolation with Laplace Kernels is a High-Dimensional Phenomenon](https://mlsanity.com/paper/1812.11167/) (2018)
- [Regularization Matters: A Nonparametric Perspective on Overparametrized Neural Network](https://mlsanity.com/paper/2007.02486/) (2020)
- [Early-stopped neural networks are consistent](https://mlsanity.com/paper/2106.05932/) (2021)
- [Simultaneous Model Selection and Optimization through Parameter-free Stochastic Learning](https://mlsanity.com/paper/1406.3816/) (2014)

## Built on by (most cited first, 5 of 5)

- [Neural Networks Efficiently Learn Low-Dimensional Representations with SGD](https://mlsanity.com/paper/2209.14863/) (2022)
- [Stability & Generalisation of Gradient Descent for Shallow Neural Networks without the Neural Tangent Kernel](https://mlsanity.com/paper/2107.12723/) (2021)
- [On the Role of Optimization in Double Descent: A Least Squares Study](https://mlsanity.com/paper/2107.12685/) (2021)
- [Towards Data-Algorithm Dependent Generalization: a Case Study on Overparameterized Linear Regression](https://mlsanity.com/paper/2202.06054/) (2022)
- [Gradient Descent Finds Over-Parameterized Neural Networks with Sharp Generalization for Nonparametric Regression](https://mlsanity.com/paper/2411.02904/) (2024)

## Abstract (arXiv)

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 ℓ 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).