• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of complexity >Robust pairwise learning with Huber loss
【24h】

Robust pairwise learning with Huber loss

机译：Robust pairwise learning with Huber loss

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相关主题

摘要

Pairwise learning naturally arises from machine learning tasks such as AUC maximization, ranking, and metric learning. In this paper we propose a new pairwise learning algorithm based on the additive noise regression model, which adopts the pairwise Huber loss and applies effectively even to the situation where the noise only satisfies a weak moment condition. Owing to the robustness of Huber loss function, this new method is resistant to heavy-tailed errors or outliers in the response variable. We establish a comparison theorem to characterize the gap between the excess generalization error and the prediction error. We derive the error bounds and convergence rates under appropriate conditions. It is worth mentioning that all the results are established under the (1 + epsilon)-th moment condition of the noise variable. It is rather weak particularly in the case of epsilon 1, which means the noise variable does not even admit a finite variance. (C) 2021 Elsevier Inc. All rights reserved.

著录项

获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号