On counterfactual inference with unobserved confounding

Speaker: Abhin Shah , CSAIL and LIDS

Date: Friday, October 06, 2023

Time: 4:00 PM to 4:30 PM Note: all times are in the Eastern Time Zone

Public: Yes

Location: Room 32-370

Event Type: Seminar

Room Description:

Host: Sharut Gupta, MIT CSAIL

Contact: Sharut Gupta, sharut@mit.edu

Relevant URL:

Speaker URL: None

Speaker Photo:

Reminders to: mitml@mit.edu, lids-seminars@mit.edu, seminars@csail.mit.edu

Reminder Subject: TALK: On counterfactual inference with unobserved confounding

Abstract: Given an observational study with n independent but heterogeneous units, our goal is to learn the counterfactual distribution for each unit using only one p-dimensional sample per unit containing covariates, interventions, and outcomes. Specifically, we allow for unobserved confounding that introduces statistical biases between interventions and outcomes as well as exacerbates the heterogeneity across units. Modeling the conditional distribution of the outcomes as an exponential family, we reduce learning the unit-level counterfactual distributions to learning n exponential family distributions with heterogeneous parameters and only one sample per distribution. We introduce a convex objective that pools all n samples to jointly learn all n parameter vectors, and provide a unit-wise mean squared error bound that scales linearly with the metric entropy of the parameter space. For example, when the parameters are s-sparse linear combination of k known vectors, the error is O(s log k/p). En route, we derive sufficient conditions for compactly supported distributions to satisfy the logarithmic Sobolev inequality. As an application of the framework, our results enable consistent imputation of sparsely missing unobserved confounders.

Speaker bio: Abhin Shah is a sixth-year Ph.D. student advised by Prof. Devavrat Shah and Prof. Greg Wornell. He is a recipient of MIT’s Jacobs Presidential Fellowship. His research interests include theoretical and applied aspects of trustworthy machine learning with a focus on causality and fairness.

Research Areas:

Impact Areas:

See other events that are part of the ML Tea.

Created by Sharut Gupta Email at Tuesday, October 03, 2023 at 12:01 PM.