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 2210.03232math.OCcs.DCcs.MA
收藏

双重平均与梯度投影:去中心化约束优化的收敛性保证

Double Averaging and Gradient Projection: Convergence Guarantees for Decentralized Constrained Optimization

Firooz Shahriari-Mehr, Ashkan Panahi

AI总结:

针对静态有向网络下的去中心化约束优化问题,提出基于双重平均与梯度投影的DAGP算法,结合分布式零空间投影实现全局最优,建立次线性收敛速率,还提出聚合下界分析方法并验证算法在多类问题中的有效性。

摘要:

我们研究静态有向通信网络下的一类通用去中心化约束优化问题,其中每个智能体仅能独占访问一个凸的、可微的局部目标项以及一个凸约束集。针对该场景,我们提出了一种名为DAGP(双重平均与梯度投影)的新型去中心化算法,其基于局部梯度、局部约束投影以及局部平均操作构建。我们通过一种名为分布式零空间投影的新型分布式跟踪技术实现了全局最优性。此外,我们证明通过一种问题约简方案,DAGP可用于求解目标项不可微的无约束问题。仅在假设目标项具有光滑性的条件下,我们研究了DAGP的收敛性,并在可行性、一致性和最优性三个维度上建立了次线性收敛速率,无需额外假设(例如强凸性)。在分析过程中,我们提出了一种优化问题收敛性分析的新方法,称之为聚合下界法,从而规避了选取Lyapunov函数的难点。为了证明该方法的通用性,我们还为光滑函数下的标准梯度下降算法提供了一种替代的收敛性证明。最后,我们给出了数值实验结果,验证了所提方法在约束和无约束问题中的有效性。特别地,我们利用DAGP为最优传输问题设计了一种分布式方案,该方案具备优异的性能和速度。

英文摘要:

We consider a generic decentralized constrained optimization problem over static, directed communication networks, where each agent has exclusive access to only one convex, differentiable, local objective term and one convex constraint set. For this setup, we propose a novel decentralized algorithm, called DAGP (Double Averaging and Gradient Projection), based on local gradients, projection onto local constraints, and local averaging. We achieve global optimality through a novel distributed tracking technique we call distributed null projection. Further, we show that DAGP can be used to solve unconstrained problems with non-differentiable objective terms with a problem reduction scheme. Assuming only smoothness of the objective terms, we study the convergence of DAGP and establish sub-linear rates of convergence in terms of feasibility, consensus, and optimality, with no extra assumption (e.g. strong convexity). For the analysis, we forego the difficulties of selecting Lyapunov functions by proposing a new methodology of convergence analysis in optimization problems, which we refer to as aggregate lower-bounding. To demonstrate the generality of this method, we also provide an alternative convergence proof for the standard gradient descent algorithm with smooth functions. Finally, we present numerical results demonstrating the effectiveness of our proposed method in both constrained and unconstrained problems. In particular, we propose a distributed scheme by DAGP for the optimal transport problem with superior performance and speed.

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。

↑