English

`local' vs. `global' parameters -- breaking the gaussian complexity barrier

Machine Learning 2015-04-10 v1 Statistics Theory Statistics Theory

Abstract

We show that if FF is a convex class of functions that is LL-subgaussian, the error rate of learning problems generated by independent noise is equivalent to a fixed point determined by `local' covering estimates of the class, rather than by the gaussian averages. To that end, we establish new sharp upper and lower estimates on the error rate for such problems.

Keywords

Cite

@article{arxiv.1504.02191,
  title  = {`local' vs. `global' parameters -- breaking the gaussian complexity barrier},
  author = {Shahar Mendelson},
  journal= {arXiv preprint arXiv:1504.02191},
  year   = {2015}
}
R2 v1 2026-06-22T09:13:14.695Z