Reproduce “Fairness-Aware Design for Contextual Experiments: Guaranteeing Reliability and Equity in Heterogeneous Subgroups” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Guangyan Gan, Ling Zhang, Yanhua Cheng, Yongxiang Tang, Kaiyuan Li, Xialong Liu, Peng Jiang
F-CTSD identifies the best treatment in each subgroup while enforcing minimum allocation shares for every treatment. It estimates rewards, optimizes a fairness-constrained allocation, tracks it while preserving exploration, and stops when evidence is sufficient across groups. In a synthetic setup, its fairness-violation score was 0.0048 versus CTSD’s 0.0081, with expected samples of 169.66 versus 114.81: a fairness–sample trade-off, not an efficiency gain.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.