Causal fairness analysis: a causal toolkit for fair machine learning

D Plečko, E Bareinboim - Foundations and Trends® in …, 2024 - nowpublishers.com
Decision-making systems based on AI and machine learning have been used throughout a
wide range of real-world scenarios, including healthcare, law enforcement, education, and …

Causal fairness analysis

D Plecko, E Bareinboim - arXiv preprint arXiv:2207.11385, 2022 - arxiv.org
Decision-making systems based on AI and machine learning have been used throughout a
wide range of real-world scenarios, including healthcare, law enforcement, education, and …

Trustworthy policy learning under the counterfactual no-harm criterion

H Li, C Zheng, Y Cao, Z Geng… - … on Machine Learning, 2023 - proceedings.mlr.press
Trustworthy policy learning has significant importance in making reliable and harmless
treatment decisions for individuals. Previous policy learning approaches aim at the well …

Principal fairness for human and algorithmic decision-making

K Imai, Z Jiang - Statistical Science, 2023 - projecteuclid.org
Using the concept of principal stratification from the causal inference literature, we introduce
a new notion of fairness, called principal fairness, for human and algorithmic decision …

Experimental evaluation of algorithm-assisted human decision-making: Application to pretrial public safety assessment

K Imai, Z Jiang, DJ Greiner, R Halen… - Journal of the Royal …, 2023 - academic.oup.com
Despite an increasing reliance on fully-automated algorithmic decision-making in our day-to-
day lives, humans still make consequential decisions. While the existing literature focuses …

Bayesian safe policy learning with chance constrained optimization: Application to military security assessment during the vietnam war

Z Jia, E Ben-Michael, K Imai - arXiv preprint arXiv:2307.08840, 2023 - arxiv.org
Algorithmic and data-driven decisions and recommendations are commonly used in high-
stakes decision-making settings such as criminal justice, medicine, and public policy. We …

Towards representation learning for weighting problems in design-based causal inference

O Clivio, A Feller, C Holmes - arXiv preprint arXiv:2409.16407, 2024 - arxiv.org
Reweighting a distribution to minimize a distance to a target distribution is a powerful and
flexible strategy for estimating a wide range of causal effects, but can be challenging in …

Starting small: Prioritizing safety over efficacy in randomized experiments using the exact finite sample likelihood

N Christy, AE Kowalski - arXiv preprint arXiv:2407.18206, 2024 - arxiv.org
We use the exact finite sample likelihood and statistical decision theory to answer questions
of``why?''and``what should you have done?''using data from randomized experiments and a …

Quantifying Individual Risk for Binary Outcome: Bounds and Inference

P Wu, P Ding, Z Geng, Y Liu - arXiv preprint arXiv:2402.10537, 2024 - arxiv.org
Understanding treatment heterogeneity is crucial for reliable decision-making in treatment
evaluation and selection. While the conditional average treatment effect (CATE) is …

Robust Bayes Treatment Choice with Partial Identification

AA Fernández, JLM Olea, C Qiu, J Stoye… - arXiv preprint arXiv …, 2024 - arxiv.org
We study a class of binary treatment choice problems with partial identification, through the
lens of robust (multiple prior) Bayesian analysis. We use a convenient set of prior …