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 2106.05536stat.MLcs.LGecon.EM
收藏

一种用于参数推断的可解释神经网络

An Interpretable Neural Network for Parameter Inference

Goethe University Frankfurt(法兰克福歌德大学)

Johann Pfitzinger

摘要:

深度神经网络在经济或金融等领域的采用受到模型结果缺乏可解释性的限制。本文提出了一种生成式神经网络结构-参数编码器神经网络(PENN)-能够估计局部后验分布的回归模型的参数。这些参数充分解释了输入方面的预测,并允许在存在复杂的异质效应和特征依赖性的情况下进行可视化、解释和推理。贝叶斯推断技术的使用提供了一种直观的机制,使局部参数估计朝着稳定的解决方案进行正规化,并减少有限数据可用性设置中的噪声拟合。所提出的神经网络特别适合于在经济和金融中的应用,其中参数推断起着重要的作用。一个资产定价问题的应用程序演示了如何PENN可以用来探索金融市场中的非线性风险动态,并比较经验的非线性效应的金融理论假设的行为。

英文摘要:

Adoption of deep neural networks in fields such as economics or finance has been constrained by the lack of interpretability of model outcomes. This paper proposes a generative neural network architecture - the parameter encoder neural network (PENN) - capable of estimating local posterior distributions for the parameters of a regression model. The parameters fully explain predictions in terms of the inputs and permit visualization, interpretation and inference in the presence of complex heterogeneous effects and feature dependencies. The use of Bayesian inference techniques offers an intuitive mechanism to regularize local parameter estimates towards a stable solution, and to reduce noise-fitting in settings of limited data availability. The proposed neural network is particularly well-suited to applications in economics and finance, where parameter inference plays an important role. An application to an asset pricing problem demonstrates how the PENN can be used to explore nonlinear risk dynamics in financial markets, and to compare empirical nonlinear effects to behavior posited by financial theory.

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。

↑