SHPRR：约束后悔预算下的最优臂识别新算法
SHPRR: An Algorithm for Pure Exploration under Constrained Regret
纯探索领域的新论文，把后悔预算当成可分配资源，比均匀分配识别得更准，搞 Bandit 的可以看看。
arXiv 论文提出 SHPRR（Sequential Halving with Proportional Regret Rationing）算法，研究固定采样轮数与后悔预算双重约束下的 Best Arm Identification 问题。论文从理论上证明 Sequential Halving 各阶段的探索后悔成本会逐步下降，并据此提出将后悔预算前置分配的策略。在合成数据与真实实例的实验中，SHPRR 的最优臂识别表现优于均匀后悔分配和现有基线方法。
SHPRR: An Algorithm for Pure Exploration under Constrained Regret
Best Arm Identification (BAI) conventionally measures the cost of experimentation by the number of samples collected. In many operational settings, however, the cost of exploration relative to a trusted baseline already in place is equally important. We study BAI under both a fixed sampling horizon and a regret budget. Unlike generic resources considered in constrained pure exploration, regret has a distinctive structure: sampling better arms is less costly relative to the baseline. We theoretically show that the regret cost of exploration decreases across the phases of Sequential Halving, a widely used pure-exploration algorithm. This observation yields improved guarantees on the probability of identifying the best arm and motivates a more effective allocation of the regret budget. We propose Sequential Halving with Proportional Regret Rationing (SHPRR), which front-loads the regret budget to allow more exploration when many arms remain. Experiments on synthetic and real-world instances show that SHPRR improves best-arm identification performance over uniform regret allocation and existing baselines.