arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1201.3283math.STstat.TH
收藏

变量有误差的判别分析的极小极大快速率

Minimax fast rates for discriminant analysis with errors in variables

Sébastien Loustau, Clément Marteau

摘要:

研究了测量误差对判别分析的影响。给定观测值$Z=X+ε$,其中$ε$表示随机噪声,目标是在两个可能的候选$f$和$g$中预测$X$的密度。我们假设我们有两个学习样本。我们的目标是接近最好的决策规则$G^\star$定义为贝叶斯风险的最小化。在无噪声情况下$(ε=0)$,极小极大快速收敛率在判别分析(参见\cite{mammen})或更一般的分类框架(参见\cite{tsybakov2004,AT})中的边际假设下是众所周知的。在本文中,我们打算建立类似的结果在嘈杂的情况下,即处理变量的错误时。我们证明了这个问题的极大极小下界,并解释如何才能达到这些利率,特别是使用经验风险最小化(ERM)方法的基础上反卷积核估计。

英文摘要:

The effect of measurement errors in discriminant analysis is investigated. Given observations $Z=X+ε$, where $ε$ denotes a random noise, the goal is to predict the density of $X$ among two possible candidates $f$ and $g$. We suppose that we have at our disposal two learning samples. The aim is to approach the best possible decision rule $G^\star$ defined as a minimizer of the Bayes risk. In the free-noise case $(ε=0)$, minimax fast rates of convergence are well-known under the margin assumption in discriminant analysis (see \cite{mammen}) or in the more general classification framework (see \cite{tsybakov2004,AT}). In this paper we intend to establish similar results in the noisy case, i.e. when dealing with errors in variables. We prove minimax lower bounds for this problem and explain how can these rates be attained, using in particular an Empirical Risk Minimizer (ERM) method based on deconvolution kernel estimators.

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。

↑