Towards Practicable Sequential Shift Detectors
Not on the map. Why?
Abstract (arXiv)
There is a growing awareness of the harmful effects of distribution shift on the performance of deployed machine learning models. Consequently, there is a growing interest in detecting these shifts before associated costs have time to accumulate. However, desiderata of crucial importance to the practicable deployment of sequential shift detectors are typically overlooked by existing works, precluding their widespread adoption. We identify three such desiderata, highlight existing works relevant to their satisfaction, and recommend impactful directions for future research.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 14 of its 38 references that are in the map. First posted on arXiv 27 Jul 2023.
Builds on
14 of 38 references.
References · 14
- 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
- 2020Learning under Concept Drift: A Reviewcited by 470
- 2020Measuring Robustness to Natural Distribution Shifts in Image Classificationcited by 452
- 2018Detecting and Correcting for Label Shift with Black Box Predictorscited by 364
- 2016Revisiting Classifier Two-Sample Testscited by 258
- 2020Learning Deep Kernels for Non-Parametric Two-Sample Testscited by 129
- 2021MMD Aggregated Two-Sample Testcited by 74
- 2021Conditional Distributional Treatment Effect with Kernel Conditional Mean Embeddings and U-Statistic Regressioncited by 40
- 2017On the Reliable Detection of Concept Drift from Streaming Unlabeled Datacited by 32
- 2021Retrain or not retrain: Conformal test martingales for change-point detectioncited by 28
- 2021Detecting Concept Drift With Neural Network Model Uncertaintycited by 21
- 2020Learning Kernel Tests Without Data Splittingcited by 19
2 more
Built on by
Not cited yet.