arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.21407stat.MEcs.LG
收藏

深度 Fréchet 回归

Deep Fréchet Regression

Department of Statistics, University of California, Davis(加州大学戴维斯分校统计系)

Su I Iao, Yidong Zhou, Hans-Georg Müller

AI总结:

本文提出深度 Fréchet 回归,用深度神经网络处理高维预测变量,并结合流形学习与局部 Fréchet 回归实现度量空间对象的映射和还原,理论上给出收敛速率,实验表明其优于现有方法。

摘要:

现代科学的进步使得度量空间中非欧几里得数据的可获得性不断提高。本文应对的是对非欧几里得响应变量与多元欧几里得预测变量之间关系进行建模的挑战。我们提出一种灵活的回归模型,能够在不施加参数假设的情况下处理高维预测变量。文中解决了两个主要挑战:非参数回归中的维数灾难,以及一般度量空间中线性结构的缺失。前者通过深度神经网络加以处理;对于后者,我们证明了利用流形学习将响应变量所在的度量空间映射到低维欧几里得空间的可行性。我们引入一种反向映射方法,采用局部 Fréchet 回归,将低维流形表示映射回原始度量空间中的对象。我们建立了理论框架,研究在有偏的相依 sub-Gaussian 噪声下深度神经网络的收敛速率。随后,通过扩展局部 Fréchet 回归的适用范围,使其能够在预测变量存在误差的情况下容纳多元预测变量,我们得到了所提回归模型的收敛速率。模拟和案例研究表明,针对概率分布和网络这两类特殊情形,所提模型在处理非欧几里得响应变量时优于现有方法。

英文摘要:

Advancements in modern science have led to the increasing availability of non-Euclidean data in metric spaces. This paper addresses the challenge of modeling relationships between non-Euclidean responses and multivariate Euclidean predictors. We propose a flexible regression model capable of handling high-dimensional predictors without imposing parametric assumptions. Two primary challenges are addressed: the curse of dimensionality in nonparametric regression and the absence of linear structure in general metric spaces. The former is tackled using deep neural networks, while for the latter we demonstrate the feasibility of mapping the metric space where responses reside to a low-dimensional Euclidean space using manifold learning. We introduce a reverse mapping approach, employing local Fréchet regression, to map the low-dimensional manifold representations back to objects in the original metric space. We develop a theoretical framework, investigating the convergence rate of deep neural networks under dependent sub-Gaussian noise with bias. The convergence rate of the proposed regression model is then obtained by expanding the scope of local Fréchet regression to accommodate multivariate predictors in the presence of errors in predictors. Simulations and case studies show that the proposed model outperforms existing methods for non-Euclidean responses, focusing on the special cases of probability distributions and networks.

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。

↑