Expectile regression via deep residual networks
Expectile regression via deep residual networks
复制标题
DOI：
10.1002/sta4.315
复制
发表时间：
2020-09
期刊：
影响因子：
1.7
通讯作者：
Yiyi Yin;H. Zou
中科院分区：
文献类型：
--
作者：
Yiyi Yin;H. Zou
期望值是概率论和统计学中期望值的一种推广。在金融学和风险管理中，期望值因其与损益率的联系以及它的一致性和可导出性而被认为是一种重要的风险度量。线性多元期望回归于1987年提出，用于估计给定一组协变量的反应的条件期望。近年来，基于梯度提升和核学习的非参数期望回归模型被提出。在本文中，我们提出了一个新的非参数期望回归模型，采用深度残差网络学习框架，并命名为期望神经网络。在模拟和真实的数据集上的大量数值研究表明，与现有的方法相比，期望神经网络具有非常有竞争力的性能。我们明确地指定了可预期神经网络的架构，以便它很容易被他人复制和使用。Expectile NN是第一个用于非参数预期回归的深度学习模型。
Expectile is a generalization of the expected value in probability and statistics. In finance and risk management, the expectile is considered to be an important risk measure due to its connection with gain–loss ratio and its coherent and elicitable properties. Linear multiple expectile regression was proposed in 1987 for estimating the conditional expectiles of a response given a set of covariates. Recently, more flexible nonparametric expectile regression models were proposed based on gradient boosting and kernel learning. In this paper, we propose a new nonparametric expectile regression model by adopting the deep residual network learning framework and name it Expectile NN. Extensive numerical studies on simulated and real datasets demonstrate that Expectile NN has very competitive performance compared with existing methods. We explicitly specify the architecture of Expectile NN so that it is easy to be reproduced and used by others. Expectile NN is the first deep learning model for nonparametric expectile regression.