Information-theoretic determination of minimax rates of convergence

• 成果类型: Article
• 署名作者: Yang, YH; Barron, A
• 署名单位: Iowa State University; Yale University
• 刊物名称: ANNALS OF STATISTICS
• ISSN/ISSBN: 0090-5364
• 发表日期: 1999
• 页码: 1564-1599
• 关键词: DENSITY-ESTIMATION; Nonparametric Regression; Neural Networks; approximation; entropy; complexity; distance; bounds; RISK

摘要

We present some general results determining minimax bounds on statistical risk for density estimation based on certain information-theoretic considerations. These bounds depend only on metric entropy conditions and are used to identify the minimax rales of convergence.