Generalization Bounds and Representation Learning for Estimation of Potential Outcomes and Causal Effects

01/21/2020
by   Fredrik D. Johansson, et al.
89

Practitioners in diverse fields such as healthcare, economics and education are eager to apply machine learning to improve decision making. The cost and impracticality of performing experiments and a recent monumental increase in electronic record keeping has brought attention to the problem of evaluating decisions based on non-experimental observational data. This is the setting of this work. In particular, we study estimation of individual-level causal effects, such as a single patient's response to alternative medication, from recorded contexts, decisions and outcomes. We give generalization bounds on the error in estimated effects based on distance measures between groups receiving different treatments, allowing for sample re-weighting. We provide conditions under which our bound is tight and show how it relates to results for unsupervised domain adaptation. Led by our theoretical results, we devise representation learning algorithms that minimize our bound, by regularizing the representation's induced treatment group distance, and encourage sharing of information between treatment groups. We extend these algorithms to simultaneously learn a weighted representation to further reduce treatment group distances. Finally, an experimental evaluation on real and synthetic data shows the value of our proposed representation architecture and regularization scheme.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/13/2016

Estimating individual treatment effect: generalization bounds and algorithms

There is intense interest in applying machine learning to problems of ca...
research
08/08/2023

Generalization bound for estimating causal effects from observational network data

Estimating causal effects from observational network data is a significa...
research
10/10/2019

Estimation of Utility-Maximizing Bounds on Potential Outcomes

Estimation of individual treatment effects is often used as the basis fo...
research
01/21/2021

Estimating Average Treatment Effects via Orthogonal Regularization

Decision-making often requires accurate estimation of treatment effects ...
research
04/30/2019

Adversarial Balancing-based Representation Learning for Causal Effect Inference with Observational Data

Learning causal effects from observational data greatly benefits a varie...
research
11/23/2020

Balance Regularized Neural Network Models for Causal Effect Estimation

Estimating individual and average treatment effects from observational d...
research
02/23/2018

Learning Weighted Representations for Generalization Across Designs

Predictive models that generalize well under distributional shift are of...

Please sign up or login with your details

Forgot password? Click here to reset