arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.03534cs.LGcs.AIstat.ML
收藏

基于神经网络的回归中概率分布拉伸的经验策略

Empirical Strategy for Stretching Probability Distribution in Neural-network-based Regression

Yonsei University(延世大学);LTS, Inc.(LTS公司);The University of Tokyo(东京大学)

Eunho Koo, Hyungjun Kim

摘要:

在人工神经网络下的回归分析中,预测性能取决于确定适当的层间权重。由于随机初始化的权重在反向传播期间在给定的损失函数下使用梯度下降过程来更新,因此损失函数结构可以显著地影响性能。在这项研究中,我们考虑了分布误差,即,两个分布(预测值和标签的分布)的不一致性作为预测误差,并提出加权经验拉伸(WES)作为一种新的损失函数来增加两个分布的重叠区域。该函数依赖于给定标签的分布,因此,它适用于任何分布形状。此外,它包含一个缩放超参数,使得适当的参数值最大化两个分布的公共部分。为了测试函数能力,我们生成理想分布曲线(单峰、偏单峰、双峰和偏双峰)作为标签,并在前馈神经网络下使用来自曲线的傅立叶提取的输入数据。一般来说,WES在广泛使用中优于损失函数,并且性能对各种噪声水平是鲁棒的。改进的结果是极值域的RMSE(即,分布的两个尾部区域)被期望用于预测非线性复杂系统中的异常事件,例如自然灾害和金融危机。

英文摘要:

In regression analysis under artificial neural networks, the prediction performance depends on determining the appropriate weights between layers. As randomly initialized weights are updated during back-propagation using the gradient descent procedure under a given loss function, the loss function structure can affect the performance significantly. In this study, we considered the distribution error, i.e., the inconsistency of two distributions (those of the predicted values and label), as the prediction error, and proposed weighted empirical stretching (WES) as a novel loss function to increase the overlap area of the two distributions. The function depends on the distribution of a given label, thus, it is applicable to any distribution shape. Moreover, it contains a scaling hyperparameter such that the appropriate parameter value maximizes the common section of the two distributions. To test the function capability, we generated ideal distributed curves (unimodal, skewed unimodal, bimodal, and skewed bimodal) as the labels, and used the Fourier-extracted input data from the curves under a feedforward neural network. In general, WES outperformed loss functions in wide use, and the performance was robust to the various noise levels. The improved results in RMSE for the extreme domain (i.e., both tail regions of the distribution) are expected to be utilized for prediction of abnormal events in non-linear complex systems such as natural disaster and financial crisis.

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。

↑