Statistical learning by sparse deep neural networks
Statistics Theory
2023-11-16 v1 Machine Learning
Methodology
Machine Learning
Statistics Theory
Abstract
We consider a deep neural network estimator based on empirical risk minimization with l_1-regularization. We derive a general bound for its excess risk in regression and classification (including multiclass), and prove that it is adaptively nearly-minimax (up to log-factors) simultaneously across the entire range of various function classes.
Cite
@article{arxiv.2311.08845,
title = {Statistical learning by sparse deep neural networks},
author = {Felix Abramovich},
journal= {arXiv preprint arXiv:2311.08845},
year = {2023}
}