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 2603.26850math.STstat.TH
收藏

带有高斯噪声的投影算子估计

Estimation of projection operators with Gaussian noise

Univ Lyon, Université Claude Bernard Lyon 1, CNRS UMR 5208, Institut Camille Jordan(里昂大学,克莱贝尔·贝尔纳·里昂第一大学,法国国家科学研究中心联合研究单位5208,卡米耶·让研究所)

Luca Castelli

AI总结:

本文研究了在子空间估计情况下随机投影算子的误差上界,基于噪声和子空间固有属性推导非渐近上界,并通过正则化估计器规避结构假设,以偏最小二乘框架为例说明。

摘要:

本文聚焦于当投影子空间被估计时的随机投影算子。我们推导了估计子空间投影与底层子空间投影之间的误差非渐近上界。所推导的上界依赖于噪声和估计子空间的内在属性。根据估计矩阵张量的分布,考虑了多种场景。上述界在Gram矩阵的结构假设下成立。引入了正则化估计器以规避该假设。在偏最小二乘(PLS)框架中,给出一个例子,其中估计子空间由PLS权重张成。

英文摘要:

This paper focuses on random projection operators when the subspace of projection is estimated. We derive non-asymptotic upper bounds on the error between the projection onto the estimated subspace and the projection onto the underlying subspace. The provided upper bounds depend on the noise and on intrinsic properties of the estimated subspace. Several scenarios are considered according to the distribution of the estimator of the matrix spanning the subspace. The aforementioned bounds are attained under a structural assumption on the Gram matrix associated with the subspace. Regularized estimators are introduced to circumvent this assumption. An example is given in the partial least square (PLS) framework where the estimated subspace is spanned by the PLS weights.

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。

↑