信息约束下的推理II:通信约束与共享随机性
Inference under Information Constraints II: Communication Constraints and Shared Randomness
摘要:
中央服务器需要基于分布在多个用户上的样本执行统计推断,每个用户可以向中心发送有限长度的消息。我们研究的问题,分布学习和身份测试在这个分布式推理设置和检查共享的随机性作为一种资源的作用。我们提出了一种通用的模拟和推断策略,该策略仅使用私有硬币通信协议,并且对于分布式学习是样本最优的。这种一般策略甚至对于私有币协议之间的分布测试也是样本最优的。有趣的是,我们提出了一个公共币协议,它在分发测试中的表现优于模拟和推断,实际上是样本最优的。我们的公共币协议的基础是一个随机散列,当应用于样本时,它将样本分布的卡方距离最小化为均匀分布。
英文摘要:
A central server needs to perform statistical inference based on samples that are distributed over multiple users who can each send a message of limited length to the center. We study problems of distribution learning and identity testing in this distributed inference setting and examine the role of shared randomness as a resource. We propose a general-purpose simulate-and-infer strategy that uses only private-coin communication protocols and is sample-optimal for distribution learning. This general strategy turns out to be sample-optimal even for distribution testing among private-coin protocols. Interestingly, we propose a public-coin protocol that outperforms simulate-and-infer for distribution testing and is, in fact, sample-optimal. Underlying our public-coin protocol is a random hash that when applied to the samples minimally contracts the chi-squared distance of their distribution to the uniform distribution.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。