Price of Fairness in Bandits: A Tight Minimax Characterization
This work introduces UCB-HARE (Harmonic Anchored Rank Exploration), which replaces uniform exploration with an inverse-weighted harmonic rank schedule protected by a certified positive-mean anchor, and proves an algorithm-independent lower bound of $\sigma(\sigma\sqrt{k^{\max(1,q)}/T})$; for $q>1$, this shows that the...