Causal Graph Discovery from Self and Mutually Exciting Time Series
Abstract
We present a generalized linear structural causal model, coupled with a novel data-adaptive linear regularization, to recover causal directed acyclic graphs (DAGs) from time series. By leveraging a recently developed stochastic monotone Variational Inequality (VI) formulation, we cast the causal discovery problem as a general convex optimization. Furthermore, we develop a non-asymptotic recovery guarantee and quantifiable uncertainty by solving a linear program to establish confidence intervals for a wide range of non-linear monotone link functions. We validate our theoretical results and show the competitive performance of our method via extensive numerical experiments. Most importantly, we demonstrate the effectiveness of our approach in recovering highly interpretable causal DAGs over Sepsis Associated Derangements (SADs) while achieving comparable prediction performance to powerful ``black-box'' models such as XGBoost. Thus, the future adoption of our proposed method to conduct continuous surveillance of high-risk patients by clinicians is much more likely.
Cite
@article{arxiv.2106.02600,
title = {Causal Graph Discovery from Self and Mutually Exciting Time Series},
author = {Song Wei and Yao Xie and Christopher S. Josef and Rishikesan Kamaleswaran},
journal= {arXiv preprint arXiv:2106.02600},
year = {2023}
}
Comments
See v2 for a previous workshop paper on Interpretable ML in Healthcare (IMLH) at ICML 2021, titled "Causal Graph Recovery for Sepsis-Associated Derangements via Interpretable Hawkes Networks". Also, see arXiv:2301.11336 for a short version with more experiments of our proposed method to learn "strict" DAGs