Synthetic Interventions

Devavrat Shah is a Professor with the Department of Electrical Engineering and Computer Science at Massachusetts Institute of Technology (MIT) since 2005. He has been the founding director of MIT Statistics and Data Science Center (SDSC) from 2016-2020. He is a member of MIT Institute for Data, Systems and Society (LIDS), MIT Computer Science and Artificial Intelligence Laboratory (CSAIL), and MIT Operation Research Center (ORC). 

Shah received his bachelor’s degree in computer science and engineering from the Indian Institute of Technology (IIT), Bombay in 1999, with the honor of the Presidents of India Gold Medal, which is awarded to the best graduating student across all engineering disciplines. He received his PhD in computer science from Stanford University in 2004 for which he received the George B. Dantzig Best Desperation Award from Institute for Operations Research and the Management Sciences (INFORMS). He was a post-doc in the Statistics department at Stanford in 2004-05, with time at MSRI, UC Berkeley. 

His current research interests include algorithms for machine learning, causal inference, and social data processing with a focus on on statistical inference and stochastic networks. His contributions span a variety of areas including resource allocation in communications networks, inference and learning on graphical models, and algorithms for social data processing including ranking, recommendations and crowdsourcing. Within the broad context of networks, his work spans a range of areas across electrical engineering, computer science and operations research. 

His work has received broad recognition including Rising Star Award from the Association for Computing Machinery (ACM) Special Interest Group for the computer systems performance evaluation community (SIGMETRICS) and the Erlang Prize from INFORMS Applied Probability Society. He received the Best Publication Award from INFORMS Applied Probability Society, Best Paper Award from INFORMS Manufacturing and Service Operations Management Society, Best Paper Award from NeurIPS, Best Paper Awards from IEEE Infocom, and Test of time paper awards (2019-2020) from ACM Sigmetrics. He is recipient of NSF CAREER Award and is distinguished alumni of his alma mater IIT Bombay. In 2013, he founded the machine learning start-up Celect (part of Nike since 2019) which helps retailer with optimizing inventory by accurate demand forecasting

A prototypical example of causal inference with observational data pertains evaluating impact of a policy, such as universal background check for gun purchase, on outcome of interest, such as gun violence, with respect to alternatives such no background check or stricter form of gun control law. Unlike setting of clinical trials where randomized control experiments are feasible, such is not feasibility for policy evaluation. To address this, we present a causal framework, synthetic interventions (SI), that extends synthetic control (SC) to the multiple treatment setting. Formally, given N units (e.g. states) and D interventions (e.g. various gun control policies),the aim of SI is to estimate the counterfactual outcome of each unit under each of the D interventions (including control). We showcase the efficacy of the SI framework on several real-world applications, such as running data-efficient A/B tests in e-commerce and correcting for bias in clinical trials due to dropouts. Finally, we show how to produce tight confidence intervals around our causal estimates. The key to our framework is connection between causal inference and tensor estimation. Based on joint work with Anish Agarwal and Dennis Shen, both at MIT.