cs.LGOct 8, 2024

Benign Overfitting for Regression with Trained Two-Layer ReLU Networks

Authors: Junhyung Park, Patrick Bloebaum, Shiva Prasad Kasiviswanathan

Organizations: *ETH Zürich, Switzerland · †Amazon · ‡Amazon

Abstract

We study the least-square regression problem with a two-layer fully-connected neural network, with ReLU activation function, trained by gradient flow. Our first result is a generalization result, that requires no assumptions on the underlying regression function or the noise other than that they are bounded. We operate in the neural tangent kernel regime, and our generalization result is developed via a decomposition of the excess risk into estimation and approximation errors, viewing gradient flow as an implicit regularizer. This decomposition in the context of neural networks is a novel perspective of gradient descent, and helps us avoid uniform convergence traps. In this work, we also establish that under the same setting, the trained network overfits to the data. Together, these results, establishes the first result on benign overfitting for finite-width ReLU networks for arbitrary regression functions.

Figures & tables

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Sharp Generalization for Nonparametric Regression in Interpolation Space by Shallow Over-Parameterized Neural Networks with Channel Attention

    Nov 1, 2026Yingzhen Yang, Ping LiNeural Network GeneralizationNonparametric Regression

  2. Benign Overfitting for General Norms and Distributions

    Sep 27, 2026Daniel Barzilai, Ohad ShamirBenign OverfittingStatistical Learning Theory