SHARPER BOUNDS FOR GAUSSIAN AND EMPIRICAL PROCESSES

• 成果类型: Article
• 署名作者: TALAGRAND, M
• 署名单位: University System of Ohio; Ohio State University
• 刊物名称: ANNALS OF PROBABILITY
• ISSN/ISSBN: 0091-1798
• DOI: 10.1214/aop/1176988847
• 发表日期: 1994
• 页码: 28-76
• 关键词: central limit-theorem; Metric Entropy; Integrability

摘要

Under natural conditions on a class F of functions on a probability space, near optimal bounds are given for the probabilities [GRAPHICS]. The method is a variation of this author's method to study the tailprobability of the supremum of a Gaussi