arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1502.02344stat.ML
收藏

交叉验证误差下界的正则化路径

Regularization Path of Cross-Validation Error Lower Bounds

Atsushi Shibagaki, Yoshiki Suzuki, Masayuki Karasuyama, Ichiro Takeuchi

摘要:

在许多机器学习任务中,仔细调整正则化参数是必不可少的,因为它对泛化性能有显著影响。然而,目前的正则化参数调整实践更多的是一门艺术而不是一门科学,例如,很难说在交叉验证(CV)中需要多少网格点来获得具有足够小的CV误差的解。在本文中,我们提出了一个新的框架计算的CV误差的下限作为正则化参数的函数,我们称之为CV误差下限的正则化路径。所提出的框架可以用于在当前最佳解的CV误差在整个正则化参数范围内可以远离最佳可能CV误差的意义上对一组解提供理论近似保证。我们证明,通过数值实验,理论上保证了在上述意义上的正则化参数的选择是可能的,合理的计算成本。

英文摘要:

Careful tuning of a regularization parameter is indispensable in many machine learning tasks because it has a significant impact on generalization performances. Nevertheless, current practice of regularization parameter tuning is more of an art than a science, e.g., it is hard to tell how many grid-points would be needed in cross-validation (CV) for obtaining a solution with sufficiently small CV error. In this paper we propose a novel framework for computing a lower bound of the CV errors as a function of the regularization parameter, which we call regularization path of CV error lower bounds. The proposed framework can be used for providing a theoretical approximation guarantee on a set of solutions in the sense that how far the CV error of the current best solution could be away from best possible CV error in the entire range of the regularization parameters. We demonstrate through numerical experiments that a theoretically guaranteed a choice of regularization parameter in the above sense is possible with reasonable computational costs.

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。

↑