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 1802.04715stat.MLcs.LG
收藏

随机最优化的在线方差缩减

Online Variance Reduction for Stochastic Optimization

Department of Computer Science, ETH Zurich(苏黎世联邦理工学院计算机科学系)

Zalán Borsos, Andreas Krause, Kfir Y. Levy

摘要:

现代随机最优化方法通常依赖于均匀采样,这对数据的基本特征是不可知的。这可能会降低收敛性,因为会产生具有高方差的估计值。一种可能的补救方法是采用非均匀重要性抽样技术,该技术考虑了数据集的结构。在这项工作中,我们研究了最近提出的设置,构成方差减少作为一个在线优化问题与强盗反馈。我们设计了一种新的和有效的算法,这种设置,找到一个序列的重要性抽样分布的竞争力与最好的固定分布在事后,这种结果的第一个。虽然我们提出了对数据点进行采样的方法,但它自然地扩展到选择坐标甚至其块。经验验证强调了我们的方法在几种情况下的好处。

英文摘要:

Modern stochastic optimization methods often rely on uniform sampling which is agnostic to the underlying characteristics of the data. This might degrade the convergence by yielding estimates that suffer from a high variance. A possible remedy is to employ non-uniform importance sampling techniques, which take the structure of the dataset into account. In this work, we investigate a recently proposed setting which poses variance reduction as an online optimization problem with bandit feedback. We devise a novel and efficient algorithm for this setting that finds a sequence of importance sampling distributions competitive with the best fixed distribution in hindsight, the first result of this kind. While we present our method for sampling datapoints, it naturally extends to selecting coordinates or even blocks of thereof. Empirical validations underline the benefits of our method in several settings.

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。

↑