arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.13591math.STstat.MEstat.TH
收藏

分位数回归神经网络:贝叶斯方法

Quantile Regression Neural Networks: A Bayesian Approach

Sanket R. Jantre, Shrijita Bhattacharya, Tapabrata Maiti

摘要:

本文介绍了一个贝叶斯神经网络估计方法的分位数回归假设非对称拉普拉斯分布(ALD)的响应变量。证明了前向神经网络分位数回归的后验分布在错误设定的ALD模型下是渐近相合的。这种一致性证明从密度估计域嵌入问题,并使用包围熵的界限来推导Hellinger邻域上的后验一致性。此一致性结果显示在隐藏节点数量随样本量增长的设置中。贝叶斯实现利用ALD密度的正态指数混合表示。该算法采用马尔可夫链蒙特卡罗(MCMC)模拟技术-- Gibbs抽样结合Metropolis-Hastings算法。我们已经在链收敛、起始值的选择和步长的上下文中解决了与上述MCMC实现相关的复杂性问题。我们已经说明了所提出的方法与模拟研究和实际数据的例子。

英文摘要:

This article introduces a Bayesian neural network estimation method for quantile regression assuming an asymmetric Laplace distribution (ALD) for the response variable. It is shown that the posterior distribution for feedforward neural network quantile regression is asymptotically consistent under a misspecified ALD model. This consistency proof embeds the problem from density estimation domain and uses bounds on the bracketing entropy to derive the posterior consistency over Hellinger neighborhoods. This consistency result is shown in the setting where the number of hidden nodes grow with the sample size. The Bayesian implementation utilizes the normal-exponential mixture representation of the ALD density. The algorithm uses Markov chain Monte Carlo (MCMC) simulation technique - Gibbs sampling coupled with Metropolis-Hastings algorithm. We have addressed the issue of complexity associated with the afore-mentioned MCMC implementation in the context of chain convergence, choice of starting values, and step sizes. We have illustrated the proposed method with simulation studies and real data examples.

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。

↑