In this thesis, we propose new theoretical frameworks for the analysis of stochastic and distributed methods with error compensation and local updates. Using these frameworks, we develop more than 20 new optimization methods, including the first linearly converging Error-Compensated SGD and the first linearly converging Local-SGD for arbitrarily heterogeneous local functions. Moreover, the thesis contains several new distributed methods with unbiased compression for distributed non-convex optimization problems. The derived complexity results for these methods outperform the previous best-known results for the considered problems. Finally, we propose a new scalable decentralized fault-tolerant distributed method, and under reasonable assumptions, we derive the iteration complexity bounds for this method that match the ones of centralized Local-SGD.
翻译:在此论文中,我们提出新的理论框架,用于分析有误差补偿和地方更新的随机和分布方法。我们利用这些框架,制定了20多个新的优化方法,包括第一个线性一致的错误补偿 SGD 和第一个线性合并的本地-SGD, 用于任意差异性本地功能。此外,该论文包含若干新的分布式方法,对分布式的非混凝土优化问题进行不偏袒的压缩。这些方法的衍生复杂性结果优于先前最著名的被考虑的问题结果。最后,我们提出了一个新的可缩放的分散式断层分布法,在合理的假设下,我们得出了这种方法的迭代复杂性界限,与集中式本地组合式组合法相匹配。