arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.05705math.OCcs.MA
收藏

分布式优化算法中的最优通信权重

On the Optimal Communication Weights in Distributed Optimization Algorithms

Sebastien Colla, Julien M. Hendrickx

AI总结:

本文证明最小化平均矩阵第二大特征值模的权重选择并非分布式优化算法的最优策略,提出基于性能估计问题(PEP)的优化方法来确定最优通信权重,并验证其优于SLEM最小化权重。

摘要:

我们证明,在分布式优化中,通过最小化平均矩阵的第二大特征值模(SLEM)来选择通信权重的普遍策略,虽然对现有理论性能界是最优的,但通常并非针对算法精确最坏情况性能的最优选择。这种精确性能可以使用性能估计问题(PEP)方法计算。因此,我们依靠PEP来构造一个优化问题,以确定在指定无向图上部署的分布式优化算法的最优通信权重。我们的结果表明,最优权重可以优于最小化平均矩阵第二大特征值模(SLEM)的权重。这表明SLEM并不是分散优化中加权网络性能的最佳表征。此外,我们还探索并比较了分布式优化中权重选择的其他启发式方法。

英文摘要:

We establish that in distributed optimization, the prevalent strategy of minimizing the second-largest eigenvalue modulus (SLEM) of the averaging matrix for selecting communication weights, while optimal for existing theoretical performance bounds, is generally not optimal regarding the exact worst-case performance of the algorithms. This exact performance can be computed using the Performance Estimation Problem (PEP) approach. We thus rely on PEP to formulate an optimization problem that determines the optimal communication weights for a distributed optimization algorithm deployed on a specified undirected graph. Our results show that the optimal weights can outperform the weights minimizing the second-largest eigenvalue modulus (SLEM) of the averaging matrix. This suggests that the SLEM is not the best characterization of weighted network performance for decentralized optimization. Additionally, we explore and compare alternative heuristics for weight selection in distributed optimization.

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。

↑