# Implicit Bias of Gradient Descent for Mean Squared Error Regression with Two-Layer Wide Neural Networks

arXiv: https://arxiv.org/abs/2006.07356 · HTML: https://mlsanity.com/paper/2006.07356/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jun 2020.

## Built on by (most cited first, 15 of 15)

- [The Implicit Bias of Adam on Separable Data](https://mlsanity.com/paper/2406.10650/) (2024)
- [Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes](https://mlsanity.com/paper/2406.06838/) (2024)
- [On the Local Complexity of Linear Regions in Deep ReLU Networks](https://mlsanity.com/paper/2412.18283/) (2024)
- [Predicting the Susceptibility of Examples to Catastrophic Forgetting](https://mlsanity.com/paper/2406.09935/) (2024)
- [Geometric structure of shallow neural networks and constructive mathcal L2 cost minimization](https://mlsanity.com/paper/2309.10370/) (2023)
- [How (Implicit) Regularization of ReLU Neural Networks Characterizes the Learned Function -- Part II: the Multi-D Case of Two Layers with Random First Layer](https://mlsanity.com/paper/2303.11454/) (2023)
- [Minimum norm interpolation by perceptra: Explicit regularization and implicit bias](https://mlsanity.com/paper/2311.06138/) (2023)
- [Constraining the outputs of ReLU neural networks](https://mlsanity.com/paper/2508.03867/) (2025)
- [Generalization Below the Edge of Stability: The Role of Data Geometry](https://mlsanity.com/paper/2510.18120/) (2025)
- [Optimal Rates of Convergence for Entropy Regularization in Discounted Markov Decision Processes](https://mlsanity.com/paper/2406.04163/) (2024)
- [Multi-Channel Hypergraph Contrastive Learning for Matrix Completion](https://mlsanity.com/paper/2411.01376/) (2024)
- [Implicit geometric regularization in flow matching via density weighted Stein operators](https://mlsanity.com/paper/2512.23956/) (2025)
- [Efficient Milling Quality Prediction with Explainable Machine Learning](https://mlsanity.com/paper/2409.10203/) (2024)
- [The Spectral Bias of Shallow Neural Network Learning is Shaped by the Choice of Non-linearity](https://mlsanity.com/paper/2503.10587/) (2025)
- [Variational Deep Learning via Implicit Regularization](https://mlsanity.com/paper/2505.20235/) (2025)

## Abstract (arXiv)

We investigate gradient descent training of wide neural networks and the corresponding implicit bias in function space. For univariate regression, we show that the solution of training a width-n shallow ReLU network is within n- 1/2 of the function which fits the training data and whose difference from the initial function has the smallest 2-norm of the second derivative weighted by a curvature penalty that depends on the probability distribution that is used to initialize the network parameters. We compute the curvature penalty function explicitly for various common initialization procedures. For instance, asymmetric initialization with a uniform distribution yields a constant curvature penalty, and thence the solution function is the natural cubic spline interpolation of the training data. hjFor stochastic gradient descent we obtain the same implicit bias result. We obtain a similar result for different activation functions. For multivariate regression we show an analogous result, whereby the second derivative is replaced by the Radon transform of a fractional Laplacian. For initialization schemes that yield a constant penalty function, the solutions are polyharmonic splines. Moreover, we show that the training trajectories are captured by trajectories of smoothing splines with decreasing regularization strength.