Answers are grounded in this paper and cite their sources.
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 L/sub 2/ 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, and hence fit our setup, the most important of which are kernel machines.
No takes yet. Share an insight, caveat, or question.
Shahar Mendelson (2002) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: