发表机构
Southern University of Science and Technology; Pengcheng Laboratory（南方科技大学; 鹏城实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对异构边缘网络中的分布式优化，提出WQ-GADMM方法，通过分组、窗口激活和量化通信降低通信成本，并建立了非凸目标下的收敛界，实验验证了其高效性。
AI 中文摘要
边缘网络中的分布式优化受到异构客户端计算能力和有限通信资源的制约。我们提出了窗口化与量化分组交替方向乘子法（WQ-GADMM），以在有限激活能力下协调分组更新并降低通信成本。客户端根据估计的计算时间进行分组。每个窗口每轮激活有限数量的组，云服务器在所有组完成一次更新后更新全局模型。该方法对下行链路和上行链路模型交换进行量化以降低通信成本，并允许有界模型陈旧性和不精确的近端局部更新。对于光滑非凸目标，我们在所述假设和参数条件下建立了平均平方Karush-Kuhn-Tucker残差界。该界包含一个随迭代次数递减的项和一个依赖于量化的误差项。在MNIST和CIFAR-10上的实验表明，12比特通信减少了通信量和模拟墙钟时间，同时保持了与全精度相当的测试准确率。12比特配置还保持了完整的组覆盖，并实现了比所评估基线更短的平均组间完成间隔。
英文摘要
Distributed optimization in edge networks is constrained by heterogeneous client computing capabilities and limited communication resources. We propose the Windowed and Quantized Group-Based Alternating Direction Method of Multipliers (WQ-GADMM) to coordinate group updates under limited activation capacity and reduce communication costs. Clients are grouped by estimated computation time. Each window activates a limited number of groups per round, and the cloud updates the global model after all groups have updated once. The method quantizes both downlink and uplink model exchanges to reduce communication costs and allows bounded model staleness and inexact proximal local updates. For smooth nonconvex objectives, we establish an average squared Karush-Kuhn-Tucker residual bound under the stated assumptions and parameter conditions. The bound consists of a term that decreases with the iteration count and a quantization-dependent error term. Experiments on MNIST and CIFAR-10 show that 12-bit communication reduces communication volume and simulated wall-clock time while maintaining test accuracy comparable to full precision. The 12-bit configuration also maintains complete group coverage and achieves shorter mean group inter-completion gaps than the evaluated baselines.
Comments13 pages, 8 figures
