F-score二元分类的最优分类率
Optimal rates for F-score binary classification
摘要:
我们研究了在$β$ -光滑假设下,对于$x \in \mathbb{R}^d$的回归函数$η(x) = \mathbb{P}(Y = 1|X = x)$,具有F-分数的二元分类的极小极大设置。我们提出了一个分类程序,在$α$ -保证金的假设下,实现了率$O(n^{--(1+α)β/(2β+d)})$的多余的F-分数。在这种情况下,可以通过在要估计的某个水平$θ^*$上对上述回归函数$η$进行阈值化来获得用于F分数的贝叶斯最优分类器。所提出的过程是在一个半监督的方式,也就是说,对于回归函数的估计,我们使用一个标记的数据集的大小$n \in \mathbb{N}$和最佳阈值$θ^*$的估计,我们使用一个未标记的数据集的大小$N \in \mathbb{N}$。有趣的是,$N \in \mathbb{N}$的值不影响收敛速度,这表明估计回归函数$η$比估计最佳阈值$θ^*$“更难”。这进一步意味着具有F分数的二进制分类的行为类似于二进制分类的标准设置。最后,我们表明,所提出的程序实现的速率是最佳的最小最大意义上的一个常数因子。
英文摘要:
We study the minimax settings of binary classification with F-score under the $β$-smoothness assumptions on the regression function $η(x) = \mathbb{P}(Y = 1|X = x)$ for $x \in \mathbb{R}^d$. We propose a classification procedure which under the $α$-margin assumption achieves the rate $O(n^{--(1+α)β/(2β+d)})$ for the excess F-score. In this context, the Bayes optimal classifier for the F-score can be obtained by thresholding the aforementioned regression function $η$ on some level $θ^*$ to be estimated. The proposed procedure is performed in a semi-supervised manner, that is, for the estimation of the regression function we use a labeled dataset of size $n \in \mathbb{N}$ and for the estimation of the optimal threshold $θ^*$ we use an unlabeled dataset of size $N \in \mathbb{N}$. Interestingly, the value of $N \in \mathbb{N}$ does not affect the rate of convergence, which indicates that it is "harder" to estimate the regression function $η$ than the optimal threshold $θ^*$. This further implies that the binary classification with F-score behaves similarly to the standard settings of binary classification. Finally, we show that the rates achieved by the proposed procedure are optimal in the minimax sense up to a constant factor.
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。