Formalizes SBFC problem and introduces T-a-S-CS algorithm that achieves instance-specific lower bound on sample complexity asymptotically for fair policy selection.
For𝛾∈ {0.5,1.0}< 𝛾 ∗, the optimal penalized policy is𝑎 4 (infeasible under hard constraints); for 𝛾∈ {5,10}> 𝛾 ∗, it is𝑎 1 (same as SBFC)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Selection of the Best Policy under Fairness Constraints for Subpopulations
Formalizes SBFC problem and introduces T-a-S-CS algorithm that achieves instance-specific lower bound on sample complexity asymptotically for fair policy selection.