arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1107.6027cs.ITmath.ITstat.ML
收藏

基于先验概率估计的检测器极小极大最优界

Minimax-Optimal Bounds for Detectors Based on Estimated Prior Probabilities

Jiantao Jiao, Lin Zhang, Robert Nowak

摘要:

在许多信号检测和分类问题中,我们知道每个假设下的分布,但不知道先验概率。本文的目的是提供理论来量化的检测性能,通过估计先验概率从标记或未标记的训练数据。误差或{ \em风险}被认为是先验概率的函数。我们证明了风险函数在真实先验概率附近是局部Lipschitz的,并且基于估计的先验概率的检测器的误差取决于风险函数在该局部的行为。在一般情况下,我们表明,基于先验概率的最大似然估计(MLE)的检测器的错误收敛到贝叶斯误差的速度为$n^{-1/2}$,其中$n$是训练数据的数量。如果风险函数的行为更有利,则基于MLE的检测器具有以$n^{-(1+α)/2}$形式的最优速率收敛到对应贝叶斯误差的误差,其中$α>0$是控制具有典型值$α= 1$的风险函数的行为的参数。极限$α\rightarrow \infty$对应于风险函数在真实概率附近平坦的情况,因此对MLE中的小误差不敏感;在这种情况下,基于MLE的检测器的误差以$n$的指数速度收敛到贝叶斯误差。我们证明了无论给定标记或未标记的训练数据,边界都是可达到的,并且在标记的情况下是极小极大最优的。

英文摘要:

In many signal detection and classification problems, we have knowledge of the distribution under each hypothesis, but not the prior probabilities. This paper is aimed at providing theory to quantify the performance of detection via estimating prior probabilities from either labeled or unlabeled training data. The error or {\em risk} is considered as a function of the prior probabilities. We show that the risk function is locally Lipschitz in the vicinity of the true prior probabilities, and the error of detectors based on estimated prior probabilities depends on the behavior of the risk function in this locality. In general, we show that the error of detectors based on the Maximum Likelihood Estimate (MLE) of the prior probabilities converges to the Bayes error at a rate of $n^{-1/2}$, where $n$ is the number of training data. If the behavior of the risk function is more favorable, then detectors based on the MLE have errors converging to the corresponding Bayes errors at optimal rates of the form $n^{-(1+α)/2}$, where $α>0$ is a parameter governing the behavior of the risk function with a typical value $α= 1$. The limit $α\rightarrow \infty$ corresponds to a situation where the risk function is flat near the true probabilities, and thus insensitive to small errors in the MLE; in this case the error of the detector based on the MLE converges to the Bayes error exponentially fast with $n$. We show the bounds are achievable no matter given labeled or unlabeled training data and are minimax-optimal in labeled case.

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。

↑