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 2004.14637stat.MLcs.LGeess.SP
收藏

分布式学习下线性回归的推广误差

Generalization Error for Linear Regression under Distributed Learning

Uppsala University(乌普萨拉大学)

Martin Hellkvist, Ayça Özçelikkale, Anders Ahlén

摘要:

分布式学习通过将计算负担分布在多个节点上来促进数据处理的规模化。尽管对分布式学习有着广泛的兴趣,但这种方法的泛化性能还没有得到很好的理解。我们通过关注线性回归设置来解决这个差距。我们考虑未知数分布在节点网络上的设置。我们提出了一个分析表征的依赖性的泛化误差的分割的未知数节点。特别是,对于过参数化的情况下,我们的研究结果表明,虽然训练数据的误差保持在相同的范围内的集中式解决方案,分布式解决方案的泛化误差显着增加相比,集中式解决方案时,在任何节点估计的未知数的数量是接近的观察数。我们进一步提供数值例子来验证我们的解析表达式。

英文摘要:

Distributed learning facilitates the scaling-up of data processing by distributing the computational burden over several nodes. Despite the vast interest in distributed learning, generalization performance of such approaches is not well understood. We address this gap by focusing on a linear regression setting. We consider the setting where the unknowns are distributed over a network of nodes. We present an analytical characterization of the dependence of the generalization error on the partitioning of the unknowns over nodes. In particular, for the overparameterized case, our results show that while the error on training data remains in the same range as that of the centralized solution, the generalization error of the distributed solution increases dramatically compared to that of the centralized solution when the number of unknowns estimated at any node is close to the number of observations. We further provide numerical examples to verify our analytical expressions.

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。

↑