arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 0909.2191math.STstat.TH
收藏

高维线性判别分析的快速收敛

Fast rate of convergence in high dimensional linear discriminant analysis

Robin Girard

摘要:

本文对高斯数据的高维线性判别进行了理论分析。研究了线性判别规则的超额风险问题。重点讨论了当样本维数p大于样本量n时,标准方法的性能较差的问题。相应的理论结果是非渐近的下界。另一方面,我们提出了两个歧视程序的基础上降维,并提供相关的收敛速度,可以是O(log(p)/n)稀疏假设下。最后,我们所有的结果依赖于一个定理,提供了简单的尖锐的超额风险和估计误差之间的关系,定义所使用的判别规则的几何参数。

英文摘要:

This paper gives a theoretical analysis of high dimensional linear discrimination of Gaussian data. We study the excess risk of linear discriminant rules. We emphasis on the poor performances of standard procedures in the case when dimension p is larger than sample size n. The corresponding theoretical results are non asymptotic lower bounds. On the other hand, we propose two discrimination procedures based on dimensionality reduction and provide associated rates of convergence which can be O(log(p)/n) under sparsity assumptions. Finally all our results rely on a theorem that provides simple sharp relations between the excess risk and an estimation error associated to the geometric parameters defining the used discrimination rule.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑