作者:Di; Xin; ZHANG经验主义过程上确界极大分类函数概率空间
摘要:So far the study of exponential bounds of an empirical process has been restricted to abounded index class of functions. The case of an unbounded index class of functions is now studiedon the basis of a new symmetrization idea and a new method of truncating the original probabilityspace; the exponential bounds of the tail probabilities for the supremum of the empirical process overan unbounded class of functions are obtained. The exponential bounds can be used to establish lawsof the logarithm for the empirical processes over unbounded classes of functions.
注:因版权方要求,不能公开全文,如需全文,请咨询杂志社