Nonparametric regression with modified ReLU networks
Not on the map. Why?
Abstract (arXiv)
We consider regression estimation with modified ReLU neural networks in which network weight matrices are first modified by a function α before being multiplied by input vectors. We give an example of continuous, piecewise linear function α for which the empirical risk minimizers over the classes of modified ReLU networks with l1 and squared l2 penalties attain, up to a logarithmic factor, the minimax rate of prediction of unknown β-smooth function.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 9 of its 20 references that are in the map. First posted on arXiv 17 Jul 2022.
Builds on
9 of 20 references.
References · 9
- 2017Nonparametric regression using deep neural networks with ReLU activation functioncited by 431
- 2018Adaptivity of deep ReLU network for learning in Besov and mixed smooth Besov spaces: optimal rate and curse of dimensionalitycited by 160
- 2020Statistical Guarantees for Regularized Neural Networkscited by 25
- 2020Nonconvex sparse regularization for deep neural networks and its optimalitycited by 21
- 2020On Deep Instrumental Variables Estimatecited by 14
- 2019Optimal Nonparametric Inference via Deep Neural Networkcited by 9
- 2020Estimation of the Mean Function of Functional Data via Deep Neural Networkscited by 8
- 2021Calibrating multi-dimensional complex ODE from noisy data via deep neural networkscited by 6
- 2017Fast learning rate of deep learning via a kernel perspectivecited by 1
Built on by
Not cited yet.