Author(s)

Weilin Nie, Cheng Wang^*

Department of Mathematics, Huizhou University, Huizhou, China.

A standard assumption in the literature of learning theory is the samples which are drawn independently from an identical distribution with a uniform bounded output. This excludes the common case with Gaussian distribution. In this paper we extend these assumptions to a general case. To be precise, samples are drawn from a sequence of unbounded and non-identical probability distributions. By drift error analysis and Bennett inequality for the unbounded random variables, we derive a satisfactory learning rate for the ERM algorithm.

Learning Theory, ERM, Non-Identical, Unbounded Sampling, Covering Number

Nie, W. and Wang, C. (2016) Error Analysis of ERM Algorithm with Unbounded and Non-Identical Sampling. Journal of Applied Mathematics and Physics, 4, 156-168. doi: 10.4236/jamp.2016.41019.