The Generalization Error of the Minimum-norm Solutions for Over-parameterized Neural Networks
Not on the map. Why?
Abstract (arXiv)
We study the generalization properties of minimum-norm solutions for three over-parametrized machine learning models including the random feature model, the two-layer neural network model and the residual network model. We proved that for all three models, the generalization error for the minimum-norm solution is comparable to the Monte Carlo rate, up to some logarithmic terms, as long as the models are sufficiently over-parametrized.
Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). First posted on arXiv 15 Dec 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 4; 2022: 1; 2023: 0; 2024: 1.
6 papers.
- 2021Generalization Error of GAN from the Discriminator's Perspectivecited by 8
- 2022A Mathematical Framework for Learning Probability Distributionscited by 7
- 2021One-pass Stochastic Gradient Descent in Overparametrized Two-layer Neural Networkscited by 3
- 2021Distribution Free Uncertainty for the Minimum Norm Solution of Over-parameterized Linear Regressioncited by 2
- 2021Data-informed Deep Optimizationcited by 1
- 2024Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Datacited by 0
- 2024Quantifying the Prediction Uncertainty of Machine Learning Models for Individual Data10 Dec 2024
- 2022A Mathematical Framework for Learning Probability Distributions22 Dec 2022
- 2021Data-informed Deep Optimization17 Jul 2021
- 2021Generalization Error of GAN from the Discriminator's Perspective8 Jul 2021
- 2021One-pass Stochastic Gradient Descent in Overparametrized Two-layer Neural Networks1 May 2021
- 2021Distribution Free Uncertainty for the Minimum Norm Solution of Over-parameterized Linear Regression14 Feb 2021