Quickest Causal Change Point Detection by Adaptive Intervention
This work addresses change point detection in causal systems, which is important for fields like healthcare or finance, but it appears incremental as it builds on existing causal modeling and monitoring techniques.
The paper tackles the problem of detecting change points in linear causal models under interventions, proposing an algorithm that centralizes changes into a single dimension and uses adaptive policies for intervention selection. The result includes theoretical first-order optimality and validation through simulations and real-world case studies, though no concrete numbers are provided.
We propose an algorithm for change point monitoring in linear causal models that accounts for interventions. Through a special centralization technique, we can concentrate the changes arising from causal propagation across nodes into a single dimension. Additionally, by selecting appropriate intervention nodes based on Kullback-Leibler divergence, we can amplify the change magnitude. We also present an algorithm for selecting the intervention values, which aids in the identification of the most effective intervention nodes. Two monitoring methods are proposed, each with an adaptive intervention policy to make a balance between exploration and exploitation. We theoretically demonstrate the first-order optimality of the proposed methods and validate their properties using simulation datasets and two real-world case studies.