Defying the gravity of learning curve: a characteristic of nearest neighbour anomaly detectors

详细信息    查看全文

• 作者：Kai Ming Ting ; Takashi Washio ; Jonathan R. Wells ; Sunil Aryal
• 关键词：Learning curve ; Anomaly detection ; Nearest neighbour ; Computational geometry ; AUC
• 刊名：Machine Learning
• 出版年：2017
• 出版时间：January 2017
• 年：2017
• 卷：106
• 期：1
• 页码：55-91
• 全文大小：
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence (incl. Robotics); Control, Robotics, Mechatronics; Computing Methodologies; Simulation and Modeling; Language Translation and Linguistics;
• 出版者：Springer US
• ISSN：1573-0565
• 卷排序：106

文摘

Conventional wisdom in machine learning says that all algorithms are expected to follow the trajectory of a learning curve which is often colloquially referred to as ‘more data the better’. We call this ‘the gravity of learning curve’, and it is assumed that no learning algorithms are ‘gravity-defiant’. Contrary to the conventional wisdom, this paper provides the theoretical analysis and the empirical evidence that nearest neighbour anomaly detectors are gravity-defiant algorithms.