arXivDaily arXiv每日学术速递 周一至周五更新
arXiv math/0703811math.STq-fin.RMstat.TH
收藏

分类中惩罚经验风险最小化的次优性

Suboptimality of Penalized Empirical Risk Minimization in Classification

Guillaume Lecué

摘要:

令$\cF$是具有$[-1,1]$中的值的$M$分类过程的集合。给定一个损失函数,我们要构造一个过程,它以尽可能好的速率模仿$\cF$中的最佳过程。这个最快的速率称为最优聚合速率。考虑连续规模的损失函数与各种类型的凸性,我们证明了最佳的聚合率可以是$((\log M)/n)^{1/2}$或$(\log M)/n$。我们证明,如果所有的$M$分类器是二进制的(惩罚)经验风险最小化程序是次优的(即使在利润率/低噪声条件下)时,损失函数是有点超过凸,而在这种情况下,指数权重的聚合程序达到最佳的聚合率。

英文摘要:

Let $\cF$ be a set of $M$ classification procedures with values in $[-1,1]$. Given a loss function, we want to construct a procedure which mimics at the best possible rate the best procedure in $\cF$. This fastest rate is called optimal rate of aggregation. Considering a continuous scale of loss functions with various types of convexity, we prove that optimal rates of aggregation can be either $((\log M)/n)^{1/2}$ or $(\log M)/n$. We prove that, if all the $M$ classifiers are binary, the (penalized) Empirical Risk Minimization procedures are suboptimal (even under the margin/low noise condition) when the loss function is somewhat more than convex, whereas, in that case, aggregation procedures with exponential weights achieve the optimal rate of aggregation.

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。

↑