Under data distributions which may be heavy-tailed, many stochastic gradient-based learning algorithms are driven by feedback queried at points with almost no performance guarantees on their own. Here we explore a modified "anytime online-to-batch" mechanism which for smooth objectives admits high-probability error bounds while requiring only lower-order moment bounds on the stochastic gradients. Using this conversion, we can derive a wide variety of "anytime robust" procedures, for which the task of performance analysis can be effectively reduced to regret control, meaning that existing regret bounds (for the bounded gradient case) can be robustified and leveraged in a straightforward manner. As a direct takeaway, we obtain an easily implemented stochastic gradient-based algorithm for which all queried points formally enjoy sub-Gaussian error bounds, and in practice show noteworthy gains on real-world data applications.
翻译:在数据分布中,许多基于梯度和梯度的学习算法都可能非常繁琐,其驱动力来自在几乎没有性能保证的点进行查询的反馈。 在这里,我们探索一个经过修改的“ 随时在线到批量” 机制,这个机制为了顺利的目标,可以接受高概率误差界限,而只要求对悬浮梯度的下级瞬间界限。 使用这一转换,我们可以产生各种各样的“随时稳健”程序,而业绩分析的任务可以有效地降低到后悔控制,这意味着现有的(对受约束梯度案例)遗憾界限可以直截了当地加以巩固和杠杆化。 作为直接取走,我们得到了一种易于实施的随机梯度梯度算法,所有被查询的点都可以正式享有亚全球误差界限,在实践中,在现实世界数据应用程序上显示出值得注意的收益。