论文标题
TOP-K数据选择通过分布式样品分位推断
Top-k data selection via distributed sample quantile inference
论文作者
论文摘要
我们考虑从分布在具有嘈杂通信链接的$ n $代理网络之间的数据集中确定最大的最大测量值的问题。我们表明，这种情况可以作为称为样品分位推理的分布式凸优化问题施放，我们使用两次尺度随机近似算法求解。在此，我们在几乎确定的意义上证明了算法的收敛性。此外，我们的算法处理噪声，并在少量迭代中融合到正确的答案。
We consider the problem of determining the top-$k$ largest measurements from a dataset distributed among a network of $n$ agents with noisy communication links. We show that this scenario can be cast as a distributed convex optimization problem called sample quantile inference, which we solve using a two-time-scale stochastic approximation algorithm. Herein, we prove the algorithm's convergence in the almost sure sense to an optimal solution. Moreover, our algorithm handles noise and empirically converges to the correct answer within a small number of iterations.
