With the growth of large data as well as large-scale learning tasks, the need for efficient and robust linear system solvers is greater than ever. The randomized Kaczmarz method (RK) and similar stochastic iterative methods have received considerable recent attention due to their efficient implementation and memory footprint. These methods can tolerate streaming data, accessing only part of the data at a time, and can also approximate the least squares solution even if the system is affected by noise. However, when data is instead affected by large (possibly adversarial) corruptions, these methods fail to converge, as corrupted data points draw iterates far from the true solution. A recently proposed solution to this is the QuantileRK method, which avoids harmful corrupted data by exploring the space carefully as the method iterates. The exploration component requires the computation of quantiles of large samples from the system and is computationally much heavier than the subsequent iteration update. In this paper, we propose an approach that better uses the information obtained during exploration by incorporating an averaged version of the block Kaczmarz method. This significantly speeds up convergence, while still allowing for a constant fraction of the equations to be arbitrarily corrupted. We provide theoretical convergence guarantees as well as experimental supporting evidence. We also demonstrate that the classical projection-based block Kaczmarz method cannot be robust to sparse adversarial corruptions, but rather the blocking has to be carried out by averaging one-dimensional projections.
翻译:随着大量数据的增长以及大规模学习任务的扩大,对高效和稳健的线性系统系统求解器的需求比以往任何时候更加迫切。随机的Kaczmarz 方法(RK)和类似的随机的随机性迭代方法最近因其高效实施和记忆足足足,受到相当的关注。这些方法可以容忍流数据,一次只访问数据的一部分,而且即使系统受到噪音的影响,也能够接近最平方的解决方案。然而,如果数据受到大规模(可能的对立)的腐败影响,则需要高效和稳健的线性系统系统求解,这些方法比以往任何时候任何时候都更需要更高效和强大的线性系统解答。但是,由于腐败数据点与真正的解决方案相距甚远,因此更需要高效和强大的线性线性系统求系统解系统解工作。然而,当数据受到大规模(可能存在的对立对立性)的腐败的腐败前期(可能是对抗性)的腐败前期,这些方法无法相互汇合,因为腐败数据点与真正的解决方案相隔得甚远。最近提出的一个解决办法是Qaltileleleler-L-L-R-RC-RC-Ring 方法,最近得到的解决方案是Q-立的解决方案,通过仔细-Qczmar-C-C-C-C-C-C-C-C-C-级的趋一致法的加速法的加速法的加速法的加速法方法避免了有害的,而避免了有害的腐败的加速化方法,通过仔细的加速化,而避免了有害的腐合。我们-我们-我们-我们-我们-------------------------我们--------------我们--我们--------------------------------------------------------------------------------------------------------------保证----------------------------------------------------------------------------------------------------------------------------------------------------------------------