Rethinking Chronological Causal Discovery with Signal Processing
This work addresses a practical issue in causal discovery for biological or physical systems, but it is incremental as it focuses on analyzing sensitivity rather than proposing a new solution.
The paper investigates how causal discovery methods are affected by mismatches between observation timing and underlying event timing, showing that both classical and recent methods are sensitive to sampling rate and window length hyperparameters.
Causal discovery problems use a set of observations to deduce causality between variables in the real world, typically to answer questions about biological or physical systems. These observations are often recorded at regular time intervals, determined by a user or a machine, depending on the experiment design. There is generally no guarantee that the timing of these recordings matches the timing of the underlying biological or physical events. In this paper, we examine the sensitivity of causal discovery methods to this potential mismatch. We consider empirical and theoretical evidence to understand how causal discovery performance is impacted by changes of sampling rate and window length. We demonstrate that both classical and recent causal discovery methods exhibit sensitivity to these hyperparameters, and we discuss how ideas from signal processing may help us understand these phenomena.