Improving the sample complexity using global data

Mendelson, Shahar

Cultural advice

The Australian National University acknowledges, celebrates and pays our respects to the Ngunnawal and Ngambri people of the Canberra region and to all First Nations Australians on whose traditional lands we meet and work, and whose cultures are among the oldest continuing cultures in human history.

Aboriginal and Torres Strait Islander peoples are advised that ANU Library collections may include images, names, voices, and other representations of deceased persons.

Material in the collection may contain terms, language or views that reflect the period in which the item was created and may be considered inappropriate today.

Improving the sample complexity using global data

Date

2002

Authors

Mendelson, Shahar

Abstract

We study the sample complexity of proper and improper learning problems with respect to different q-loss functions. We improve the known estimates for classes which have relatively small covering numbers in empirical L2 spaces (e.g., log-covering numbers which are polynomial with exponent p < 2). We present several examples of relevant classes which have a "small" fat-shattering dimension, hence fit our setup, the most important of which are kernel machines.