Distributed Networked Learning with Correlated Data
Distributed Networked Learning with Correlated Data
复制标题
DOI：
10.1109/cdc42340.2020.9304091
复制
发表时间：
2020-12
期刊：
影响因子：
--
通讯作者：
Lingzhou Hong;Alfredo García;Ceyhun Eksin
中科院分区：
文献类型：
--
作者：
Lingzhou Hong;Alfredo García;Ceyhun Eksin
本文考虑了跨节点分布的异质和相关数据的学习问题。我们提出了一个分布式学习方案，每个节点异步都会实现随机梯度下降更新，并将其当前模型与邻居交换。我们通过对最小二乘问题的网络正则罚款来确保本地模型之间的相似性和集合平均值。这种惩罚与与本地模型相对准确性成正比的权重有关。我们进一步提供了基于惩罚常数和网络连接性的本地模型与集成平均模型之间差异的有限时间表征。我们将提出的方法与总体最小二乘和逻辑回归进行比较，以基于头部运动数据的个人活动预测。
This paper considers a learning problem with heteroscedastic and correlated data that is distributed across nodes. We propose a distributed learning scheme where each node asynchronously implements stochastic gradient descent updates and exchanges their current models with neighbors. We ensure the similarity among the local models and the ensemble average by having a network regularization penalty to the least squares problem. This penalty is associated with weights that are proportional to the relative accuracy of local models. We further provide finite time characterization of the disparity between local models and the ensemble average model based on the penalty constants and network connectivity. We compare the proposed method with generalized least squares and logistic regression in the prediction of activities of individuals based on head movement data.