arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1609.06385stat.MLcs.LG
收藏

多类分类校准功能

Multiclass Classification Calibration Functions

University of Alberta(阿尔伯塔大学)

Bernardo Ávila Pires, Csaba Szepesvári

摘要:

在本文中,我们完善的过程中计算校准功能的多类分类代理损失。校准函数是一个强大的工具,可以轻松地将替代风险的界限(可以通过众所周知的方法计算)转换为真实风险的界限,即犯错误的概率。它们特别适用于非参数设置,其中近似误差可以控制,并且提供比通过替代损失上限0-1损失的常见技术更严格的界限。更复杂的现有校准函数结果的抽象性质要求在逐个情况的基础上明确地导出校准函数,每当需要新的替代损失的界限时,都需要重复的努力。我们设计了一个精简的分析,简化了大量的替代损失,已在文献中提出的推导校准函数的过程。推导校准函数的努力,然后推测在验证中,对于一个选定的替代损失,少量的条件,我们介绍。作为案例研究,我们恢复了Lee等人(2004)的已知损失的现有校准函数,并为已知损失提供了新的校准函数,包括一对所有损失和逻辑斯谛回归损失,以及过去已被证明是分类校准的许多其他损失,但没有导出校准函数。

英文摘要:

In this paper we refine the process of computing calibration functions for a number of multiclass classification surrogate losses. Calibration functions are a powerful tool for easily converting bounds for the surrogate risk (which can be computed through well-known methods) into bounds for the true risk, the probability of making a mistake. They are particularly suitable in non-parametric settings, where the approximation error can be controlled, and provide tighter bounds than the common technique of upper-bounding the 0-1 loss by the surrogate loss. The abstract nature of the more sophisticated existing calibration function results requires calibration functions to be explicitly derived on a case-by-case basis, requiring repeated efforts whenever bounds for a new surrogate loss are required. We devise a streamlined analysis that simplifies the process of deriving calibration functions for a large number of surrogate losses that have been proposed in the literature. The effort of deriving calibration functions is then surmised in verifying, for a chosen surrogate loss, a small number of conditions that we introduce. As case studies, we recover existing calibration functions for the well-known loss of Lee et al. (2004), and also provide novel calibration functions for well-known losses, including the one-versus-all loss and the logistic regression loss, plus a number of other losses that have been shown to be classification-calibrated in the past, but for which no calibration function had been derived.

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。

↑