Operationalizing Complex Causes: A Pragmatic View of Mediation
This addresses a practical challenge in causal inference for domains such as genomics or image processing, offering an incremental improvement by formalizing and providing initial solutions for crude interventions.
The paper tackles the problem of estimating causal effects for complex objects like text or images when only indirect interventions are available, proposing a two-step method and testing procedure that efficiently estimates effects with limited data from new treatments.
We examine the problem of causal response estimation for complex objects (e.g., text, images, genomics). In this setting, classical \emph{atomic} interventions are often not available (e.g., changes to characters, pixels, DNA base-pairs). Instead, we only have access to indirect or \emph{crude} interventions (e.g., enrolling in a writing program, modifying a scene, applying a gene therapy). In this work, we formalize this problem and provide an initial solution. Given a collection of candidate mediators, we propose (a) a two-step method for predicting the causal responses of crude interventions; and (b) a testing procedure to identify mediators of crude interventions. We demonstrate, on a range of simulated and real-world-inspired examples, that our approach allows us to efficiently estimate the effect of crude interventions with limited data from new treatment regimes.