English

Extending the scope of the small-ball method

Machine Learning 2020-06-16 v2

Abstract

The small-ball method was introduced as a way of obtaining a high probability, isomorphic lower bound on the quadratic empirical process, under weak assumptions on the indexing class. The key assumption was that class members satisfy a uniform small-ball estimate: that Pr(fκfL2)δPr(|f| \geq \kappa\|f\|_{L_2}) \geq \delta for given constants κ\kappa and δ\delta. Here we extend the small-ball method and obtain a high probability, almost-isometric (rather than isomorphic) lower bound on the quadratic empirical process. The scope of the result is considerably wider than the small-ball method: there is no need for class members to satisfy a uniform small-ball condition, and moreover, motivated by the notion of tournament learning procedures, the result is stable under a `majority vote'.

Keywords

Cite

@article{arxiv.1709.00843,
  title  = {Extending the scope of the small-ball method},
  author = {Shahar Mendelson},
  journal= {arXiv preprint arXiv:1709.00843},
  year   = {2020}
}
R2 v1 2026-06-22T21:32:08.459Z