AI4OPT Seminar Series
Date: Thursday, April 6, 2023
Time: Noon – 1:00 pm
Location: Instructional Center 115 (Scale Up Room) - (759 Ferst Dr, Atlanta, GA 30318)
Join Virtually: https://gatech.zoom.us/j/99381428980
Speaker: Devavrat Shah
On Counterfactual Inference With Unobserved Confounding via Exponential Family
Abstract: We are interested in the problem of unit-level counterfactual inference with unobserved confounders owing to the increasing importance of personalized decision-making in many domains: consider a recommender system interacting with a user over time where each user is provided recommendations based on observed demographics, prior engagement levels as well as certain unobserved factors. The system adapts its recommendations sequentially and differently for each user. Ideally, at each point in time, the system wants to infer each user's unknown engagement if it were exposed to a different sequence of recommendations while everything else remained unchanged. This task is challenging since: (a) the unobserved factors could give rise to spurious associations, (b) the users could be heterogeneous, and (c) only a single trajectory per user is available.
We model the underlying joint distribution through an exponential family. This reduces the task of unit-level counterfactual inference to simultaneously learning a collection of distributions of a given exponential family with different unknown parameters with single observation per distribution. We discuss a computationally efficient method for learning all of these parameters with estimation error scaling linearly with the metric entropy of the space of unknown parameters – if the parameters are s-sparse linear combination of k known vectors in p dimension, the error scales as O(s log k/p). En route, we derive sufficient conditions for compactly supported distributions to satisfy the logarithmic Sobolev inequality.
Based on joint work with Raaz Dwivedi, Abhin Shah, and Greg Wornell (of MIT).
Bio: Devavrat Shah is the Andrew (1956) and Erna Viterbi professor of Electrical Engineering and Computer Science at Massachusetts Institute of Technology (MIT) since 2005. He is the faculty director of Deshpande Center for Tech Innovation, and the founding director of the Statistics and Data Science Center at MIT between 2016 to 2020. His current research interests include algorithms for causal inference, social data processing and stochastic networks. Shah is a distinguished alumni of his alma mater IIT Bombay. His work has been recognized through career prizes 2008 ACM Sigmetrics Rising Star and 2010 INFORMS Erlang Prize; paper prizes at IEEE Infocom, ACM Sigmetrics, NeurIPS, INFORMS Applied Probability Society, INFORM Management Science and Operations Management; INFORMS George B Dantzig thesis prize and test of time awards at ACM Sigmetrics. In 2013, Shah co-founded the machine learning start-up Celect (part of Nike) which helps retailers optimize inventory using accurate demand forecasting. In 2019, he co-founded Ikigai Labs with the mission of building a self-driving organization by empowering data business operators to build AI Apps with the ease of spreadsheets.
Lunch will be served at the seminar. So, please stop by 15 minutes before the seminar to pick up lunch.
To receive AI4OPT seminar announcements, please sign up to our mailing list. at https://lists.isye.gatech.edu/mailman/listinfo/ai4opt-seminars.
Past seminars can be found at https://www.ai4opt.org/seminars/past-seminars.