RENORMALIZING UPPER AND LOWER BOUNDS FOR INTEGRATED RISK IN THE WHITE-NOISE MODEL

• 成果类型: Article
• 署名作者: LOW, MG
• 刊物名称: ANNALS OF STATISTICS
• ISSN/ISSBN: 0090-5364
• DOI: 10.1214/aos/1176349137
• 发表日期: 1993
• 页码: 577-589
• 关键词: convergence; rates

摘要

Renormalization arguments are used to derive optimal rates of convergence, under integrated squared error loss, for parameter spaces having a certain rectangular structure.