中文

基于组合奖励兼惩罚损失函数的支持向量回归

机器学习 2020-05-05 v2 机器学习

摘要

本文引入一种新颖的组合奖励兼惩罚损失函数来处理回归问题。所提出的组合奖励兼惩罚损失函数对位于回归器 ϵ\epsilon-tube 之外的数据点进行惩罚,并对位于回归器 ϵ\epsilon-tube 之内的数据点给予奖励。基于该组合奖励兼惩罚损失函数的回归(RP-ϵ\epsilon-SVR)模型具有若干有趣的性质,本文对其进行了研究,并通过实验结果予以支持。

关键词

引用

@article{arxiv.1904.12331,
  title  = {Support Vector Regression via a Combined Reward Cum Penalty Loss Function},
  author = {Pritam Anand and Reshma Rastogi and Suresh Chandra},
  journal= {arXiv preprint arXiv:1904.12331},
  year   = {2020}
}

备注

For any assistance , reader can contact on email with Pritam Anand. Email id - [email protected]. The valuable opinion/comments on the work are welcomed. Looking for collaboration especially for speeding up the solution of optimization problems