English

Learning bounded subsets of $L_p$

Machine Learning 2020-02-05 v1 Machine Learning Statistics Theory Statistics Theory

Abstract

We study learning problems in which the underlying class is a bounded subset of LpL_p and the target YY belongs to LpL_p. Previously, minimax sample complexity estimates were known under such boundedness assumptions only when p=p=\infty. We present a sharp sample complexity estimate that holds for any p>4p > 4. It is based on a learning procedure that is suited for heavy-tailed problems.

Keywords

Cite

@article{arxiv.2002.01182,
  title  = {Learning bounded subsets of $L_p$},
  author = {Shahar Mendelson},
  journal= {arXiv preprint arXiv:2002.01182},
  year   = {2020}
}
R2 v1 2026-06-23T13:30:27.009Z