We propose a decentralized penalty method for general convex constrained multi-agent optimization problems. Each auxiliary penalized problem is solved approximately with a special parallel descent splitting method. The method can be implemented in a computational network where each agent sends information only to the nearest neighbours. Convergence of the method is established under rather weak assumptions. We also describe a specialization of the proposed approach to the feasibility problem.

中文翻译：

---

基于惩罚方法的分散式多智能体优化

我们提出了一种用于一般凸约束多智能体优化问题的分散惩罚方法。每个辅助惩罚问题都用一种特殊的平行下降分裂方法近似求解。该方法可以在计算网络中实现，其中每个代理只向最近的邻居发送信息。该方法的收敛性是在相当弱的假设下建立的。我们还描述了针对可行性问题的拟议方法的专门化。