Garud Iyengar

Bio:

Garud Iyengar is the Avanessians Director of the Columbia Data Science Institute, and a Professor in the IEOR Department at Columbia Engineering. He received his B. Tech. in Electrical Engineering from IIT Kanpur, and an MS and PhD in Electrical Engineering from Stanford University. His research interests are broadly in control, machine learning and optimization. His current projects focus on the areas of large-scale power systems and supply chains, causal inference, and modeling of cellular processes. He was elected an INFORMS Fellow in 2018.

Title of talk:

Scalable Computation of Causal Bounds

Abstract of talk:

We consider the problem of computing bounds for causal inference problems with unobserved confounders, where identifiability does not hold. Existing non-parametric approaches for computing such bounds use linear programming (LP) formulations that become quickly intractable for existing solvers because the size of the LP grows exponentially in the number of edges in the underlying causal graph. We show that this LP can be significantly pruned by carefully considering the structure of the causal query. This pruning procedure allows us to compute the bound in nearly closed form for a special class of causal graphs and queries, which includes a well-studied family of problems where multiple confounded treatments influence a outcome. We also propose a very efficient greedy heuristic that matches the LP bounds for all problems for which the LP can be solved, and can compute bounds for problems that are larger by several orders of magnitude. Joint work with Madhu Shridharan (IEOR)