Efficient Local and Global Causal Discovery: Methods Leveraging Causal Substructures for Improved Finite Sample Performance

Title: Efficient Local and Global Causal Discovery: Methods Leveraging Causal Substructures for Improved Finite Sample Performance

Abstract: In this talk, we introduce two complementary methods for local and global causal discovery that leverage causal substructures for improved finite-sample performance. The first method, under an additive noise model (ANM) setting, exploits ancestral relationships to produce a more informative topological ordering than traditional linear orderings, generalizing to nonlinear causal relationships. The second method is a constraint-based approach that focuses on efficiently identifying valid adjustment sets (VAS) for confounding control, without relying on parametric or pretreatment assumptions. Both methods offer theoretical guarantees, run in polynomial time, and are empirically validated on synthetic data. Together, they highlight how harnessing local and global structures can reduce computational overhead, enhance accuracy in identifying causal edges, and improve downstream inference in observational studies.

Bio: Kyra Gan is an assistant professor in the School of Operations Research and Information Engineering and Cornell Tech at Cornell University. She is a field member of ORIE, Center for Applied Mathematics (CAM), and Statistics. She is also affiliated with the WCM Institute of AI for Digital Health. Prior to Cornell Tech, she was a postdoctoral fellow at the Statistical Reinforcement Lab at Harvard University. She received her Ph.D. in Operations Research in 2022 from Carnegie Mellon University.
Her research focuses on the design of adaptive and online algorithms for personalized treatment, such as micro-randomized trials and N-of-1 trials, in constrained settings. She is also interested in robust and efficient statistical inference for data collected in both adaptive and nonadaptive settings, robust and scalable causal discovery methods, and improving fairness in healthcare treatment outcomes.