We consider the problem of online local false discovery rate (FDR) control where multiple tests are conducted sequentially, with the goal of maximizing the total expected number of discoveries. We formulate the problem as an online resource allocation problem with accept/reject decisions, which from a high level can be viewed as an online knapsack problem, with the additional uncertainty of exogenous random budget replenishment. We start with general arrival distributions and propose a simple policy that achieves a $O(\sqrt{T})$ regret. We complement the result by showing that such regret rate is in general not improvable. We then shift our focus to discrete arrival distributions. We find that many existing re-solving heuristics in the online resource allocation literature, albeit achieve bounded loss in canonical settings, may incur a $\Omega(\sqrt{T})$ or even a $\Omega(T)$ regret. With the observation that canonical policies tend to be too optimistic and over accept arrivals, we propose a novel policy that incorporates budget buffers. We show that small additional logarithmic buffers suffice to reduce the regret from $\Omega(\sqrt{T})$ or even $\Omega(T)$ to $O(\ln^2 T)$. Numerical experiments are conducted to validate our theoretical findings. Our formulation may have wider applications beyond the problem considered in this paper, and our results emphasize how effective policies should be designed to reach a balance between circumventing wrong accept and reducing wrong reject in online resource allocation problems with exogenous budget replenishment.

翻译：暂无翻译