5 papers
Observationally Informed Adaptive Causal Experimental Design
Erdun Gao, Liang Zhang, Jake Fawkes +5
Randomized Controlled Trials (RCTs) represent the gold standard for causal inference yet remain a scarce resource. While large-scale observational data is often available, it is ut…
Causal-EPIG: A Prediction-Oriented Active Learning Framework for CATE Estimation
Erdun Gao, Jake Fawkes, Dino Sejdinovic
Estimating the Conditional Average Treatment Effect (CATE) is often constrained by the high cost of obtaining outcome measurements, making active learning essential. However, conve…
The Hardness of Validating Observational Studies with Experimental Data
Jake Fawkes, Michael O'Riordan, Athanasios Vlontzos +2
Observational data is often readily available in large quantities, but can lead to biased causal effect estimates due to the presence of unobserved confounding. Recent works attemp…
The Fragility of Fairness: Causal Sensitivity Analysis for Fair Machine Learning
Jake Fawkes, Nic Fishman, Mel Andrews +1
Fairness metrics are a core tool in the fair machine learning literature (FairML), used to determine that ML models are, in some sense, "fair". Real-world data, however, are typica…
Is merging worth it? Securely evaluating the information gain for causal dataset acquisition
Jake Fawkes, Lucile Ter-Minassian, Desi Ivanova +2
Merging datasets across institutions is a lengthy and costly procedure, especially when it involves private information. Data hosts may therefore want to prospectively gauge which…