arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2102.07767cs.LGcs.DCcs.MAmath.OCstat.ML
收藏

基于压缩信念的通信高效分布式协作学习

Communication-efficient Distributed Cooperative Learning with Compressed Beliefs

Department of Electrical and Computer Engineering, Rice University(莱斯大学电气与计算机工程系);Rice University(莱斯大学);Houston, TX, USA(美国得克萨斯州休斯敦(此处地址信息不满足机构提取要求,仅保留有效机构部分))

Mohammad Taha Toghani, César A. Uribe

摘要:

我们研究分布式协作学习的问题,其中一组代理商寻求同意一组假设,最好地描述了一系列的私人观察。在假设集是大的情况下,我们提出了一个信念更新规则,代理共享压缩(稀疏或量化)的信念与任意的正压缩率。我们的算法利用了一个统一的通信规则,使代理访问广泛的压缩运算符作为黑盒模块。我们证明了几乎必然渐近指数收敛的信念周围的最佳假设。此外,我们显示了一个非渐近的,明确的,和线性的概率集中率的信念的最佳假设集。我们提供了数值实验来说明我们的方法的通信优势。仿真结果表明,在所研究的场景中,传输的比特数可以减少到非压缩方法的5-10%。

英文摘要:

We study the problem of distributed cooperative learning, where a group of agents seeks to agree on a set of hypotheses that best describes a sequence of private observations. In the scenario where the set of hypotheses is large, we propose a belief update rule where agents share compressed (either sparse or quantized) beliefs with an arbitrary positive compression rate. Our algorithm leverages a unified communication rule that enables agents to access wide-ranging compression operators as black-box modules. We prove the almost sure asymptotic exponential convergence of beliefs around the set of optimal hypotheses. Additionally, we show a non-asymptotic, explicit, and linear concentration rate in probability of the beliefs on the optimal hypothesis set. We provide numerical experiments to illustrate the communication benefits of our method. The simulation results show that the number of transmitted bits can be reduced to 5-10% of the non-compressed method in the studied scenarios.

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。

↑