PM-CuSum mixes predictive distributions from multiple window lengths with adaptive weighting to achieve first-order asymptotic optimality in sequential change detection with a smaller remainder order in the delay bound than single fixed-window methods.
arXiv preprint arXiv:2504.02818 , year=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
Proposes an e-process-based sequential diagnostic that detects misspecified PDE inverse problem fits earlier than standard discrepancy methods while providing anytime-valid type-I error control.
A new e-statistic enables anytime-valid sequential testing by betting on predictions from unlabeled data, with non-trivial power for binary outcomes even under inaccurate predictions and label or concept shift.
citing papers explorer
-
Adaptive Sequential Change Detection using Mixtures of Predictive Distributions
PM-CuSum mixes predictive distributions from multiple window lengths with adaptive weighting to achieve first-order asymptotic optimality in sequential change detection with a smaller remainder order in the delay bound than single fixed-window methods.
-
Sequential Structure-Sensitive Residual Diagnostics for PDE Inverse Problems
Proposes an e-process-based sequential diagnostic that detects misspecified PDE inverse problem fits earlier than standard discrepancy methods while providing anytime-valid type-I error control.
-
Semi-Supervised Hypothesis Testing by Betting on Predictions
A new e-statistic enables anytime-valid sequential testing by betting on predictions from unlabeled data, with non-trivial power for binary outcomes even under inaccurate predictions and label or concept shift.