论文标题
分散的二元优化
Decentralized Bilevel Optimization
论文作者
论文摘要
二重性优化已成功应用于许多重要的机器学习问题。在各种设置下，已经研究了用于求解双层优化的算法。在本文中，我们研究了在分散的设置下的非convex-rong-convex双杆优化。我们为确定性和随机二聚体优化问题设计了分散的算法。此外，我们分析了在差异方案中所提出算法的收敛速率，包括在跨代理商之间观察到数据异质性的情况。关于合成数据和实际数据的数值实验表明所提出的方法是有效的。
Bilevel optimization has been successfully applied to many important machine learning problems. Algorithms for solving bilevel optimization have been studied under various settings. In this paper, we study the nonconvex-strongly-convex bilevel optimization under a decentralized setting. We design decentralized algorithms for both deterministic and stochastic bilevel optimization problems. Moreover, we analyze the convergence rates of the proposed algorithms in difference scenarios including the case where data heterogeneity is observed across agents. Numerical experiments on both synthetic and real data demonstrate that the proposed methods are efficient.
