Probably Approximately Correct Causal Discovery
This addresses the foundational challenge of efficient causal inference in fields like AI and epidemiology, though it appears incremental as it applies existing learning theory to causal methods.
The authors tackled the problem of causal discovery under resource constraints by proposing the Probably Approximately Correct Causal (PACC) Discovery framework, which extends PAC learning principles to causal methods, providing theoretical guarantees for techniques like propensity scores and instrumental variables that previously lacked them.
The discovery of causal relationships is a foundational problem in artificial intelligence, statistics, epidemiology, economics, and beyond. While elegant theories exist for accurate causal discovery given infinite data, real-world applications are inherently resource-constrained. Effective methods for inferring causal relationships from observational data must perform well under finite data and time constraints, where "performing well" implies achieving high, though not perfect accuracy. In his seminal paper A Theory of the Learnable, Valiant highlighted the importance of resource constraints in supervised machine learning, introducing the concept of Probably Approximately Correct (PAC) learning as an alternative to exact learning. Inspired by Valiant's work, we propose the Probably Approximately Correct Causal (PACC) Discovery framework, which extends PAC learning principles to the causal field. This framework emphasizes both computational and sample efficiency for established causal methods such as propensity score techniques and instrumental variable approaches. Furthermore, we show that it can also provide theoretical guarantees for other widely used methods, such as the Self-Controlled Case Series (SCCS) method, which had previously lacked such guarantees.