Over-parametrized deep neural networks minimizing the empirical risk do not generalize well
From MaRDI portal
Publication:1983625
DOI10.3150/21-BEJ1323zbMath1504.62052arXiv1912.03925OpenAlexW3195511373MaRDI QIDQ1983625
Publication date: 10 September 2021
Published in: Bernoulli (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1912.03925
Nonparametric regression and quantile regression (62G08) Asymptotic properties of nonparametric inference (62G20) Artificial neural networks and deep learning (68T07) Neural nets and related approaches to inference from stochastic processes (62M45) Statistical aspects of big data and data science (62R07)
Related Items
Convergence rates for shallow neural networks learned by gradient descent, On the rate of convergence of image classifiers based on convolutional neural networks, Analysis of convolutional neural network image classifiers in a hierarchical max-pooling model with additional local pooling
Cites Work
- Unnamed Item
- Additive regression and other nonparametric models
- Distribution-free consistency results in nonparametric discrimination and regression function estimation
- The use of polynomial splines and their tensor products in multivariate function estimation. (With discussion)
- Optimal global rates of convergence for nonparametric regression
- A distribution-free theory of nonparametric regression
- Nonparametric regression using deep neural networks with ReLU activation function
- Rejoinder: ``Nonparametric regression using deep neural networks with ReLU activation function
- On deep learning as a remedy for the curse of dimensionality in nonparametric regression
- Benign overfitting in linear regression
- Reconciling modern machine-learning practice and the classical bias–variance trade-off
- Nonparametric Regression Based on Hierarchical Interaction Models