Balancing interference and correlation in spatial experimental designs: a causal graph cut approach

Zhu, Jin ORCID: 0000-0001-8550-5822, Li, Jingyi, Zhou, Hongyi, Lin, Yinan, Lin, Zhenhua and Shi, Chengchun ORCID: 0000-0001-7773-2099 (2025) Balancing interference and correlation in spatial experimental designs: a causal graph cut approach. In: Proceedings of the 42nd International Conference on Machine Learning. ACM Press. (In Press)

Text (Cluster_Design___Graph_Cut) - Accepted Version Download (1MB)

Abstract

This paper focuses on the design of spatial experiments to optimize the amount of information derived from the experimental data and enhance the accuracy of the resulting causal effect estimator. We propose a surrogate function for the mean squared error (MSE) of the estimator, which facilitates the use of classical graph cut algorithms to learn the optimal design. Our proposal offers three key advances: (1) it accommodates moderate to large spatial interference effects; (2) it adapts to different spatial covariance functions; (3) it is computationally efficient. Theoretical results and numerical experiments based on synthetic environments and a dispatch simulator that models a city-scale ridesharing market, further validate the effectiveness of our design. A python implementation of our method is available at https://github. com/Mamba413/CausalGraphCut.

Item Type:	Book Section
Additional Information:	© 2025 The Author(s)
Divisions:	Statistics
Date Deposited:	27 Jun 2025 14:09
Last Modified:	27 Jun 2025 15:45
URI:	http://eprints.lse.ac.uk/id/eprint/128238

Actions (login required)

View Item