Xin Cui — Quant • HFT • ML

New algorithm reduces unfairness in bandit problems by balancing exploration and exploitation.

problem Fairness in bandit problems where early participants can be unfairly disadvantaged.

method Introduces extsf{UCB-HARE} algorithm that balances exploration and exploitation using inverse-weighted harmonic rank schedule.

result Algorithm extsf{UCB-HARE} achieves regret matching the lower bound

Ω(σ\sqrt{k^{\max(1,q)}/T})

for

q>1

arXiv research