We derive minimax testing errors in a distributed framework where the data is split over multiple machines and their communication to a central machine is limited to $b$ bits. We investigate both the $d$- and infinite-dimensional signal detection problem under Gaussian white noise. We also derive distributed testing algorithms reaching the theoretical lower bounds. Our results show that distributed testing is subject to fundamentally different phenomena that are not observed in distributed estimation. Among our findings, we show that testing protocols that have access to shared randomness can perform strictly better in some regimes than those that do not. We also observe that consistent nonparametric distributed testing is always possible, even with as little as $1$-bit of communication and the corresponding test outperforms the best local test using only the information available at a single local machine. Furthermore, we also derive adaptive nonparametric distributed testing strategies and the corresponding theoretical lower bounds.
翻译:我们在一个分布式框架中得出微最大测试错误,在这个框架中,数据在多个机器之间被分割,而它们与中央机器的通信仅限于1美元比特。我们调查高西亚白色噪音下的美元和无限维信号探测问题。我们还得出了分布式测试算法,达到理论下限。我们的结果表明,分布式测试受到在分布式估算中未观察到的截然不同的现象的影响。在我们的研究结果中,我们显示,在有些制度中,能够共享随机性的测试协议可以比不共享的测试程序更严格地运行。我们还注意到,始终一致的非参数分布式测试总是可能的,即使通信只有1美元比特,相应的测试也只能使用单一的本地机器的现有信息,从而超越了最佳的本地测试。此外,我们还得出了适应性的非参数分布式测试策略和相应的理论下限。