arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.09969cs.LGstat.ML
收藏

基于样本压缩的非对称空间分类

Classification in asymmetric spaces via sample compression

Ariel University(阿里埃勒大学)

Lee-Ad Gottlieb, Shira Ozeri

摘要:

我们在拟度量空间中开始了严格的分类研究。这些点集具有非负的距离函数,也满足三角不等式,但不对称。本文提出并改进了一种基于样本压缩和最近邻的准度量的学习算法,并证明了它具有良好的统计特性。

英文摘要:

We initiate the rigorous study of classification in quasi-metric spaces. These are point sets endowed with a distance function that is non-negative and also satisfies the triangle inequality, but is asymmetric. We develop and refine a learning algorithm for quasi-metrics based on sample compression and nearest neighbor, and prove that it has favorable statistical properties.

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。

↑