Reproduce “Fair Bayesian Optimization” 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

Valerio Perrone, Michele Donini, Muhammad Bilal Zafar, Robin Schmucker, Krishnaram Kenthapadi, Cédric Archambeau

FairBO searches model hyperparameters for settings meeting a user-selected fairness threshold while maintaining accuracy. It estimates performance and fairness through Bayesian optimization, prioritizing feasible settings before optimizing performance. On Adult, with a Statistical Parity difference (DSP) limit of 0.05, it reached the fair optimum in five times fewer evaluations than random search; this validation result does not establish fairness beyond that criterion.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.