English

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.

Keywords

Cite

@article{arxiv.2311.08845,
  title  = {Statistical learning by sparse deep neural networks},
  author = {Felix Abramovich},
  journal= {arXiv preprint arXiv:2311.08845},
  year   = {2023}
}
R2 v1 2026-06-28T13:21:54.713Z