图 书 馆
一般多类损失的分类标准尺寸Classification Calibration Dimension for General Multiclass Losses |
|
| 课程网址: | http://videolectures.net/machine_guruprasad_general/ |
| 主讲教师: | Harish Guruprasad |
| 开课单位: | 印度科学研究所 |
| 开课时间: | 2013-01-14 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | We study consistency properties of surrogate loss functions for general multiclass classification problems, defined by a general loss matrix. We extend the notion of classification calibration, which has been studied for binary and multiclass 0-1 classification problems (and for certain other specific learning problems), to the general multiclass setting, and derive necessary and sufficient conditions for a surrogate loss to be classification calibrated with respect to a loss matrix in this setting. We then introduce the notion of \emph{classification calibration dimension} of a multiclass loss matrix, which measures the smallest `size' of a prediction space for which it is possible to design a convex surrogate that is classification calibrated with respect to the loss matrix. We derive both upper and lower bounds on this quantity, and use these results to analyze various loss matrices. In particular, as one application, we provide a different route from the recent result of Duchi et al.\ (2010) for analyzing the difficulty of designing `low-dimensional' convex surrogates that are consistent with respect to pairwise subset ranking losses. We anticipate the classification calibration dimension may prove to be a useful tool in the study and design of surrogate losses for general multiclass learning problems. |
| 关 键 词: | 一般多类分类问题; 损失函数; 二进制; 标准尺寸 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2020-06-15：heyf |
| 阅读次数: | 40 |