Christopher Harshaw is an Assistant Professor in the Statistics Department at Columbia University. His research focuses on causal inference and algorithm design, particularly in improving the design and analysis of randomized experiments, including experiments with interference and sequential experiments. He holds a PhD in Computer Science from Yale University and completed postdoctoral fellowships at MIT/UC Berkeley (via FODSI) and the Simons Institute for the Theory of Computing. Education: PhD in Computer Science (Yale University), Postdoctoral Fellowships at MIT/UC Berkeley and the Simons Institute. Research Interests: At the intersection of computation and statistics. Key areas include causal inference methodologies, algorithmic tools for experimental design, and submodular optimization. His work emphasizes balancing covariates, handling interference in experiments, and developing efficient experimental frameworks. Notable Achievements: Received the Best Paper Award at the CML4Impact NeurIPS 2022 Workshop and the Best Paper Award at CISRC 2016. His contributions include the Gram-Schmidt Walk Design for covariate balancing and the Conflict Graph Design for causal effect estimation under interference. Labs/Teams: Collaborations include work on software packages such as GSWDesign.jl and SubmodularGreedy.jl, advancing tools for statistical experimentation and submodular optimization.





