Inspired by recent work of Islamov et al (2021), we propose a family of Federated Newton Learn (FedNL) methods, which we believe is a marked step in the direction of making second-order methods applicable to FL. In contrast to the aforementioned work, FedNL employs a different Hessian learning technique which i) enhances privacy as it does not rely on the training data to be revealed to the coordinating server, ii) makes it applicable beyond generalized linear models, and iii) provably works with general contractive compression operators for compressing the local Hessians, such as Top-$K$ or Rank-$R$, which are vastly superior in practice. Notably, we do not need to rely on error feedback for our methods to work with contractive compressors. Moreover, we develop FedNL-PP, FedNL-CR and FedNL-LS, which are variants of FedNL that support partial participation, and globalization via cubic regularization and line search, respectively, and FedNL-BC, which is a variant that can further benefit from bidirectional compression of gradients and models, i.e., smart uplink gradient and smart downlink model compression. We prove local convergence rates that are independent of the condition number, the number of training data points, and compression variance. Our communication efficient Hessian learning technique provably learns the Hessian at the optimum. Finally, we perform a variety of numerical experiments that show that our FedNL methods have state-of-the-art communication complexity when compared to key baselines.
翻译:在Islamov等人(2021年)最近工作的启发下,我们提出一个Feded Newton Learning(FedNL)方法(FedNL)家族,我们认为这是使第二阶方法适用于FL的一个显著步骤。与上述工作不同,FedNL采用不同的Hessian学习技术,这(一)加强了隐私,因为它不依赖向协调服务器披露的培训数据,(二)使其适用于超越通用线性模型,(三)与一般的精密压缩操作员合作,以压缩当地的赫赛人,例如高K$或Ren-R$。我们认为,这是在实际中大大优于第二阶方法的一步。值得注意的是,我们不需要依靠错误反馈来利用我们的方法与合同制压缩师一起工作。 此外,我们开发了FedNL-P、FedNL-CR和FedNL-L-LS,这是FNL的变式,它支持部分参与,而全球化则分别通过直线搜索和直线搜索,而FedNL-BC,这是一个变式,它可以进一步受益于双向级的精度压缩速度的精确的精确压缩,我们学习了精度的精度的精度的精度和精度数据。