arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1806.09178stat.MLcs.LG
收藏

随机傅立叶特征的统一分析

Towards A Unified Analysis of Random Fourier Features

University of Oxford(牛津大学);King’s College London(伦敦国王学院)

Zhu Li, Jean-Francois Ton, Dino Oglic, Dino Sejdinovic

摘要:

随机傅立叶特征是一种广泛使用的简单有效的核方法扩展技术。然而,现有的理论分析的方法,仍然集中在特定的学习任务,并通常给出悲观的界限,这是不一致的实证结果。我们解决了这些问题,并提供了第一个统一的风险分析学习与随机傅立叶特征使用平方误差和Lipschitz连续损失函数。在我们的边界,计算成本和预期的风险收敛速度之间的权衡是特定于问题的,并表示在正则化参数和\emph{number of effective degrees of freedom}。我们研究了标准的随机傅立叶特征的方法,我们提高了现有的界限,以保证相应的极小极大风险的核岭回归收敛速度所需的功能的数量,以及一个数据相关的修改,采样功能成比例的\emph{ridge leverage scores},进一步减少了所需的功能数量。由于岭杠杆分数是昂贵的计算,我们设计了一个简单的近似方案,可证明降低了计算成本,而不损失统计效率。

英文摘要:

Random Fourier features is a widely used, simple, and effective technique for scaling up kernel methods. The existing theoretical analysis of the approach, however, remains focused on specific learning tasks and typically gives pessimistic bounds which are at odds with the empirical results. We tackle these problems and provide the first unified risk analysis of learning with random Fourier features using the squared error and Lipschitz continuous loss functions. In our bounds, the trade-off between the computational cost and the expected risk convergence rate is problem specific and expressed in terms of the regularization parameter and the \emph{number of effective degrees of freedom}. We study both the standard random Fourier features method for which we improve the existing bounds on the number of features required to guarantee the corresponding minimax risk convergence rate of kernel ridge regression, as well as a data-dependent modification which samples features proportional to \emph{ridge leverage scores} and further reduces the required number of features. As ridge leverage scores are expensive to compute, we devise a simple approximation scheme which provably reduces the computational cost without loss of statistical efficiency.

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。

↑