arXiv Open Access 2015

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

Shahar Mendelson

Lihat Sumber

Abstrak

We show that if $F$ is a convex class of functions that is $L$-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.

Topik & Kata Kunci

stat.ML math.ST

Penulis (1)

Shahar Mendelson

Format Sitasi

APA MLA BibTeX

Mendelson, S. (2015). `local' vs. `global' parameters -- breaking the gaussian complexity barrier. https://arxiv.org/abs/1504.02191

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2015
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓