During the last decade, we have witnessed a paradigm shift in the data that may be collected. While performing large-scale randomized experiments has long been prohibitively expensive, the possibility of large-scale experiments — for example, using CRISPR perturbations in the biomedical sciences, field experiments in the social sciences, and digital experimentation — has led to a complete change in the type of data that can be obtained at scale. Observational data, even accompanied by strong assumptions, can paint only a partial picture of the underlying causal mechanisms. However, with sufficient interventional data, causal effects can be learned with much weaker assumptions.
With the floodgates open, the challenge is to control the deluge: the main difficulty in these applications lies in the heterogeneous treatment effects in large-scale experiments as well as the combinatorial explosion of the possible interventions that can be performed including experimental design in dynamical systems, sequential designs, and online experimentation. Despite the vast increase in possibilities, it remains, in general, simply not feasible to perform all possible interventions. It is therefore critical to develop a theory of experimental design for causal inference that informs which experiments to run in order to extract as much causal information as possible.
This workshop aims to integrate ideas from experimental design, active learning, policy learning, and contextual bandits, and showcase empirical work of interventions for causal inference in the social sciences, biology, medicine, and beyond.
Registration is required to attend this boot camp. Space may be limited, and you are advised to register early. The link to the registration form will appear on this page approximately 10 weeks before the boot camp. Please await confirmation of your acceptance before booking your travel.
Further details about this workshop will be posted in due course. To contact the organizers about this workshop, please complete this form.
Please note: the Simons Institute regularly captures photos and video of activity around the Institute for use in videos, publications, and promotional materials.
Anish Agarwal (MIT), Arnab Bhattacharyya (National University of Singapore, Singapore), James Cussens (University of Bristol), Sandrine Dudoit (UC Berkeley), Raaz Dwivedi (Harvard University), Frederick Eberhardt (Caltech), Emily Fox (Stanford), Nathan Kallus (Cornell University), Shiva Kasiviswanathan (Amazon), Murat Kocaoglu (Purdue Univeristy), Ron Kohavi (), Ismael Mourifie (University of Toronto), Razieh Nabi (Emory University), Emilija Perković (University of Washington), Maya Petersen (UC Berkeley), James Robins (Harvard University), Devavrat Shah (Massachusetts Institute of Technology), Uri Shalit (Technion - Israel Institute of Technology), Karthikeyan Shanmugam (IBM), Dennis Shen (UC Berkeley), Liam Solus (KTH), Scott Sussex (ETH Zurich), Vasilis Syrgkanis (Microsoft Research), Fredrik Sävje (Yale University), Yan Shuo Tan (UC Berkeley), Jin Tian (Iowa State University), Caroline Uhler (MIT), Jingshen Wang (UC Berkeley), Ting Ye (University of Washington), Bin Yu (UC Berkeley), Kun Zhang (Carnegie Mellon University)