arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.00846math.STstat.MEstat.TH
收藏

Sobolev椭球上在线非参数回归的筛法随机梯度下降估计

A Sieve Stochastic Gradient Descent Estimator for Online Nonparametric Regression in Sobolev ellipsoids

Tianyu Zhang, Noah Simon

摘要:

回归的目标是恢复一个未知的潜在函数,该函数将一组预测因子与噪声观测的结果最好地联系起来。在非参数回归中,假设回归函数属于预先指定的无限维函数空间(假设空间)。在在线设置中,当观测值以流的形式出现时,计算上优选迭代地更新估计值,而不是重复地重新调整整个模型。受非参数筛法估计和随机逼近方法的启发,当假设空间为Sobolev椭球时,提出了一种筛法随机梯度下降估计(Sieve-SGD).我们证明了Sieve-SGD在一组简单而直接的条件下具有速率最优均方误差(MSE)。所提出的估计可以构建一个低的计算(时间和空间)费用:我们还正式表明,Sieve-SGD需要几乎最小的内存使用所有统计率最优估计。

英文摘要:

The goal of regression is to recover an unknown underlying function that best links a set of predictors to an outcome from noisy observations. In nonparametric regression, one assumes that the regression function belongs to a pre-specified infinite-dimensional function space (the hypothesis space). In the online setting, when the observations come in a stream, it is computationally-preferable to iteratively update an estimate rather than refitting an entire model repeatedly. Inspired by nonparametric sieve estimation and stochastic approximation methods, we propose a sieve stochastic gradient descent estimator (Sieve-SGD) when the hypothesis space is a Sobolev ellipsoid. We show that Sieve-SGD has rate-optimal mean squared error (MSE) under a set of simple and direct conditions. The proposed estimator can be constructed with a low computational (time and space) expense: We also formally show that Sieve-SGD requires almost minimal memory usage among all statistically rate-optimal estimators.

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。

↑