Testing for concept shift online
Not on the map. Why?
Abstract (arXiv)
This note continues study of exchangeability martingales, i.e., processes that are martingales under any exchangeable distribution for the observations. Such processes can be used for detecting violations of the IID assumption, which is commonly made in machine learning. Violations of the IID assumption are sometimes referred to as dataset shift, and dataset shift is sometimes subdivided into concept shift, covariate shift, etc. Our primary interest is in concept shift, but we will also discuss exchangeability martingales that decompose perfectly into two components one of which detects concept shift and the other detects what we call label shift. Our methods will be based on techniques of conformal prediction.
Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Dec 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 4; 2022: 3; 2023: 0; 2024: 2; 2025: 4; 2026: 1.
14 papers.
Sort:
- 2021Testing for Outliers with Conformal p-valuescited by 133
- 2022Conformal Prediction Under Feedback Covariate Shift for Biomolecular Designcited by 53
- 2021Tracking the risk of a deployed model and detecting harmful distribution shiftscited by 38
- 2024Protected Test-Time Adaptation via Online Entropy Matching: A Betting Approachcited by 22
- 2025WATCH: Adaptive Monitoring for AI Deployments via Weighted-Conformal Martingalescited by 13
- 2022Fair When Trained, Unfair When Deployed: Observable Fairness Measures are Unstable in Performative Prediction Settingscited by 11
- 2022A unified framework for dataset shift diagnosticscited by 7
- 2021Conformal testing in a binary model situationcited by 4
- 2026Testing For Distribution Shifts with Conditional Conformal Test Martingalescited by 3
- 2024Diagnostic Runtime Monitoring with Martingalescited by 2
- 2021Enhancement of prediction algorithms by bettingcited by 1
- 2025Efficient Learning Under Density Shift in Incremental Settings Using Cram'er-Rao-Based Regularizationcited by 0
- 2026Testing For Distribution Shifts with Conditional Conformal Test Martingales14 Feb 2026
- 2025Adapting to Fragmented and Evolving Data: A Fisher Information Perspective25 Jul 2025
- 2025A Conformal Predictive Measure for Assessing Catastrophic Forgetting15 May 2025
- 2025WATCH: Adaptive Monitoring for AI Deployments via Weighted-Conformal Martingales7 May 2025
- 2025Efficient Learning Under Density Shift in Incremental Settings Using Cram'er-Rao-Based Regularization18 Feb 2025
- 2024Protected Test-Time Adaptation via Online Entropy Matching: A Betting Approach14 Aug 2024
- 2024Diagnostic Runtime Monitoring with Martingales31 Jul 2024
- 2022A unified framework for dataset shift diagnostics17 May 2022
- 2022Fair When Trained, Unfair When Deployed: Observable Fairness Measures are Unstable in Performative Prediction Settings10 Feb 2022
- 2022Conformal Prediction Under Feedback Covariate Shift for Biomolecular Design8 Feb 2022
- 2021Tracking the risk of a deployed model and detecting harmful distribution shifts12 Oct 2021
- 2021Enhancement of prediction algorithms by betting18 May 2021
2 more
- 2021Testing for Outliers with Conformal p-values16 Apr 2021
- 2021Conformal testing in a binary model situation5 Apr 2021
- 2021Testing for Outliers with Conformal p-valuescited by 133
- 2022Conformal Prediction Under Feedback Covariate Shift for Biomolecular Designcited by 53
- 2021Tracking the risk of a deployed model and detecting harmful distribution shiftscited by 38
- 2024Protected Test-Time Adaptation via Online Entropy Matching: A Betting Approachcited by 22
- 2025WATCH: Adaptive Monitoring for AI Deployments via Weighted-Conformal Martingalescited by 13
- 2022Fair When Trained, Unfair When Deployed: Observable Fairness Measures are Unstable in Performative Prediction Settingscited by 11
- 2022A unified framework for dataset shift diagnosticscited by 7
- 2021Conformal testing in a binary model situationcited by 4
- 2026Testing For Distribution Shifts with Conditional Conformal Test Martingalescited by 3
- 2024Diagnostic Runtime Monitoring with Martingalescited by 2
- 2021Enhancement of prediction algorithms by bettingcited by 1
- 2025Efficient Learning Under Density Shift in Incremental Settings Using Cram'er-Rao-Based Regularizationcited by 0
12 most cited of 14 All 14 (JSON)
- 2026Testing For Distribution Shifts with Conditional Conformal Test Martingales14 Feb 2026
- 2025Adapting to Fragmented and Evolving Data: A Fisher Information Perspective25 Jul 2025
- 2025A Conformal Predictive Measure for Assessing Catastrophic Forgetting15 May 2025
- 2025WATCH: Adaptive Monitoring for AI Deployments via Weighted-Conformal Martingales7 May 2025
- 2025Efficient Learning Under Density Shift in Incremental Settings Using Cram'er-Rao-Based Regularization18 Feb 2025
- 2024Protected Test-Time Adaptation via Online Entropy Matching: A Betting Approach14 Aug 2024
- 2024Diagnostic Runtime Monitoring with Martingales31 Jul 2024
- 2022A unified framework for dataset shift diagnostics17 May 2022
- 2022Fair When Trained, Unfair When Deployed: Observable Fairness Measures are Unstable in Performative Prediction Settings10 Feb 2022
- 2022Conformal Prediction Under Feedback Covariate Shift for Biomolecular Design8 Feb 2022
- 2021Tracking the risk of a deployed model and detecting harmful distribution shifts12 Oct 2021
- 2021Enhancement of prediction algorithms by betting18 May 2021
12 newest of 14 All 14 (JSON)