On Classification-Calibration of Gamma-Phi Losses

arxiv(2023)

引用 0|浏览2
暂无评分
摘要
Gamma-Phi losses constitute a family of multiclass classification loss functions that generalize the logistic and other common losses, and have found application in the boosting literature. We establish the first general sufficient condition for the classification-calibration of such losses. In addition, we show that a previously proposed sufficient condition is in fact not sufficient.
更多
查看译文
关键词
losses,classification-calibration,gamma-phi
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要