We resolve the min-max complexity of distributed stochastic convex optimization (up to a log factor) in the intermittent communication setting, where $M$ machines work in parallel over the course of $R$ rounds of communication to optimize the objective, and during each round of communication, each machine may sequentially compute $K$ stochastic gradient estimates. We present a novel lower bound with a matching upper bound that establishes an optimal algorithm.

翻译：我们解决了间歇通信环境中分布式蒸馏孔雀优化(最高为一个日志系数)的最小复杂性,在这种环境中,机器在以R$为单位的通信周期中平行工作,以优化目标;在每轮通信中,每台机器可按顺序计算以K$为单位的蒸馏梯度估计值。 我们提出了一个新颖的下限,配有匹配的上限,以建立最佳算法。