The notion of concept drift refers to the phenomenon that the distribution, which is underlying the observed data, changes over time; as a consequence machine learning models may become inaccurate and need adjustment. Many unsupervised approaches for drift detection rely on measuring the discrepancy between the sample distributions of two time windows. This may be done directly, after some preprocessing (feature extraction, embedding into a latent space, etc.), or with respect to inferred features (mean, variance, conditional probabilities etc.). Most drift detection methods can be distinguished in what metric they use, how this metric is estimated, and how the decision threshold is found. In this paper, we analyze structural properties of the drift induced signals in the context of different metrics. We compare different types of estimators and metrics theoretically and empirically and investigate the relevance of the single metric components. In addition, we propose new choices and demonstrate their suitability in several experiments.
IncA-DES: An incremental and adaptive dynamic ensemble selection approach using online K-d tree neighborhood search for data streams with concept drift
LIVIA, École de Technologie Supérieure, University of Qu\'ebec, Montreal, Qu\'ebec, Canada；Department of Informatics, Universidade Federal do Paran\' a (UFPR), Curitiba (PR), Brazil
Out-of-Distribution Detection and Data Drift Monitoring using Statistical Process Control
Office of Science and Engineering Laboratories（科学与工程实验室办公室）；Center for Devices and Radiological Health（设备与放射健康中心）；U.S. Food and Drug Administration（美国食品药品监督管理局）；Johns Hopkins University（约翰斯·霍普金斯大学）；University of Maryland（马里兰大学）；University of Maryland School of Medicine（马里兰大学医学院）
A General Framework for Estimating Preferences Using Response Time Data
Department of Economics, University of California, Berkeley（加州大学伯克利分校经济学系）；Department of Computer Science, Rice University（里德大学计算机科学系）；Departments of Electrical Engineering and Computer Sciences and Statistics, University of California, Berkeley（加州大学伯克利分校电子工程与计算机科学及统计学系；巴黎Inria）；Inria Paris
