arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1306.3574stat.ML
收藏

早期停止和非参数回归:一个最优的数据依赖停止规则

Early stopping and non-parametric regression: An optimal data-dependent stopping rule

Garvesh Raskutti, Martin J. Wainwright, Bin Yu

摘要:

提前停止策略是一种基于为迭代算法选择停止时间的正则化技术。针对再生核希尔伯特空间中的非参数回归问题,分析了应用于最小二乘损失函数的梯度下降形式的早期停止策略。我们提出了一个数据相关的停止规则,不涉及持有或交叉验证数据,我们证明了上界的平方误差的函数估计,测量的$L^2(P)$和$L^2(P_n)$规范。这些上界导致各种核类的最小最大最优速率,包括Sobolev光滑类和其他形式的再生核希尔伯特空间。我们通过模拟表明,我们的停止规则相比,有利的其他两个停止规则,一个是基于坚持的数据,另一个基于斯坦的无偏风险估计。我们还建立了我们的早期停止策略和解决方案之间的核岭回归估计路径的紧密联系。

英文摘要:

The strategy of early stopping is a regularization technique based on choosing a stopping time for an iterative algorithm. Focusing on non-parametric regression in a reproducing kernel Hilbert space, we analyze the early stopping strategy for a form of gradient-descent applied to the least-squares loss function. We propose a data-dependent stopping rule that does not involve hold-out or cross-validation data, and we prove upper bounds on the squared error of the resulting function estimate, measured in either the $L^2(P)$ and $L^2(P_n)$ norm. These upper bounds lead to minimax-optimal rates for various kernel classes, including Sobolev smoothness classes and other forms of reproducing kernel Hilbert spaces. We show through simulation that our stopping rule compares favorably to two other stopping rules, one based on hold-out data and the other based on Stein's unbiased risk estimate. We also establish a tight connection between our early stopping strategy and the solution path of a kernel ridge regression estimator.

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。

↑