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 2401.03136math.OC
收藏

异步去中心化优化与约束:有向图中的收敛速度分析

Asynchronous Decentralized Optimization with Constraints: Achievable Speeds of Convergence for Directed Graphs

Chalmers University of Technology(查尔姆斯理工大学)

Firooz Shahriari-Mehr, Ashkan Panahi

AI总结:

本文提出了一种异步双平均和梯度投影算法,用于解决有向图中去中心化优化问题,通过引入线性二次PEP方法,实现了无需强凸性假设的收敛速度分析。

摘要:

我们解决了一个去中心化的凸优化问题,其中每个代理都有其独特的局部目标函数和约束集。代理以不同的速度计算,其通信可能延迟且具有方向性。为此,我们提出了一种异步双平均和梯度投影(ASY-DAGP)算法。我们的算法通过使用本地缓冲区和利用传输消息中的时间相关性来处理诸如消息失败等困难场景。我们通过性能估计问题(PEP)保证了算法的收敛速度。特别是,我们引入了线性二次(LQ)PEP的概念。这种方法简化了光滑凸优化问题的分析,超越了Lyapunov函数分析,并避免了诸如强凸性等限制性假设。数值实验验证了我们所提算法的有效性。

英文摘要:

We address a decentralized convex optimization problem, where every agent has its unique local objective function and constraint set. Agents compute at different speeds, and their communication may be delayed and directed. For this setup, we propose an asynchronous double averaging and gradient projection (ASY-DAGP) algorithm. Our algorithm handles difficult scenarios such as message failure, by employing local buffers and utilizing the temporal correlation in the transmitted messages. We guarantee the convergence speed of our algorithm using performance estimation problems (PEP). In particular, we introduce the concept of the linear quadratic (LQ) PEP. This approach simplifies the analysis of smooth convex optimization problems, going beyond Lyapunov function analyses and avoiding restrictive assumptions such as strong-convexity. Numerical experiments validate the effectiveness of our proposed algorithm.

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。

↑