DJAM: Distributed Jacobi Asynchronous Method for Learning Personal Models
DJAM: Distributed Jacobi Asynchronous Method for Learning Personal Models
复制标题
DOI：
10.1109/lsp.2018.2859596
复制
发表时间：
2018-03
影响因子：
3.9
通讯作者：
Inês Almeida;J. Xavier
中科院分区：
文献类型：
--
作者：
Inês Almeida;J. Xavier
处理由代理网络收集的数据通常归结为解决优化问题。这些问题的分布式本质要求方法本身是分布式的。虽然大多数协作学习问题需要智能体达成共同（或共识）模型，但在某些情况下，共识解决方案可能不是最佳的。例如，代理可能希望在与邻居达成一致和最小化个人损失函数之间达成妥协。我们提出了DJAM，雅可比式分布式算法学习个性化模型。这个方法是实现友好的：它没有需要调优的超参数，它是异步的，它的更新只需要单邻居交互。我们证明了DJAM以概率1收敛到解，条件是个人损失函数是强凸的且具有Lipschitz梯度。然后，我们给出的证据表明，DJAM是等同于国家的最先进的方法：我们的方法达到了一个解决方案的错误类似于一个仔细调整的交替方向的乘数法（ADMM）在大约相同数量的单邻居相互作用的错误。
Processing data collected by a network of agents often boils down to solving an optimization problem. The distributed nature of these problems calls for methods that are, themselves, distributed. While most collaborative learning problems require agents to reach a common (or consensus) model, there are situations in which the consensus solution may not be optimal. For instance, agents may want to reach a compromise between agreeing with their neighbors and minimizing a personal loss function. We present DJAM, a Jacobi-like distributed algorithm for learning personalized models. This method is implementation-friendly: it has no hyperparameters that need tuning, it is asynchronous, and its updates only require single-neighbor interactions. We prove that DJAM converges with probability one to the solution, provided that the personal loss functions are strongly convex and have Lipschitz gradient. We then give evidence that DJAM is on par with state-of-the-art methods: our method reaches a solution with error similar to the error of a carefully tuned alternating direction method of multipliers (ADMM) in about the same number of single-neighbor interactions.