WATCH: Adaptive Monitoring for AI Deployments via Weighted-Conformal Martingales
Responsibly deploying artificial intelligence (AI) / machine learning (ML) systems in high-stakes settings arguably requires not only proof of system reliability, but moreover continual, post-deployment monitoring to quickly detect and address any unsafe behavior. Statistical methods for nonparametric change-point detection -- especially the tools of conformal test martingales (CTMs) and anytime-valid inference -- offer promising approaches to this monitoring task. However, existing methods are restricted to monitoring limited hypothesis classes or ``alarm criteria'' (such as data shifts that violate certain exchangeability assumptions), do not allow for online adaptation in response to shifts, and/or do not enable root-cause analysis of any degradation. In this paper, we expand the scope of these monitoring methods by proposing a weighted generalization of conformal test martingales (WCTMs), which lay a theoretical foundation for online monitoring for any unexpected changepoints in the data distribution while controlling false-alarms. For practical applications, we propose specific WCTM algorithms that adapt online to mild covariate shifts (in the marginal input distribution) while quickly detecting and diagnosing more severe shifts, such as concept shifts (in the conditional label distribution) or extreme (out-of-support) covariate shifts that cannot be easily adapted to. On real-world datasets, we demonstrate improved performance relative to state-of-the-art baselines.
Code (1)
Tasks
Change Point DetectionSimilar Papers 제목 키워드 기반
Adaptive Conformal Anomaly Detection with Time Series Foundation Models for Signal Monitoring
We propose a post-hoc adaptive conformal anomaly detection method for monitoring time series that leverages predictions from pre-trained foundation models without requiring additional fine-tuning. Our method yields an in…
Anomaly DetectionConformal Changepoint Localization and Root Cause Analysis with Corrupted Observations
Detecting when the statistical behavior of an engineered system changes, and identifying which component is responsible, are core problems in the monitoring of telecommunication networks, robotic platforms, security infr…
Online Shift Detection and Conformal Adaptation for Deployed Safety Classifiers
Reasoning models deployed as safety monitors exhibit a systematic vulnerability: reasoning-token budget starvation. Adversarial inputs require $3.3\times$ more reasoning tokens than benign inputs to produce valid safety …
Out-of-Distribution DetectionImproved conformalized quantile regression
Conformalized quantile regression is a procedure that inherits the advantages of conformal prediction and quantile regression. That is, we use quantile regression to estimate the true conditional quantile and then apply …
Conformal PredictionPredictionPrediction Intervalsquantile regression+1Spectral Adaptive Conformal Prediction for Structured Non-Exchangeable Data
Conformal prediction gives prediction intervals with finite-sample coverage when the data are exchangeable. Many time-indexed datasets are not exchangeable. They have seasons, recurring regimes, changing frequencies, or …