arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.14802econ.GNq-fin.EC
收藏

具有稳定同伦的经济学启发神经网络

Economics-Inspired Neural Networks with Stabilizing Homotopies

Marlon Azinovic, Jan Žemlička

摘要:

用于计算高维动态随机经济模型近似均衡的当代基于深度学习的解决方案方法通常面临两个痛点。第一个问题是,损失函数通常编码一组不同的均衡条件,如市场出清和家庭或企业的最优条件。因此,训练算法在这些可能非常不同的平衡条件之间权衡误差。这使得对其余错误的解释具有挑战性。第二个问题是,只有在相应的均衡条件下,多资产模型中的投资组合选择才会出现低误差。在培训开始时,这可能会导致不同资产的政策波动,从而阻碍培训过程。为了缓解这些问题,我们提出了两个互补的创新。首先,我们介绍市场出清层,这是一种神经网络架构,可以自动执行经济中的所有市场出清条件和借贷约束。将经济约束编码到神经网络架构中减少了损失函数中的项的数量,并增强了剩余均衡误差的可解释性。此外,我们提出了一种同伦算法来解决多资产投资组合选择问题,它改善了深度学习背景下出现的数值不稳定性。为了说明我们的方法,我们求解了一个具有两种永久风险厌恶类型、三种不同资产和总冲击的世代交叠模型。

英文摘要:

Contemporary deep learning based solution methods used to compute approximate equilibria of high-dimensional dynamic stochastic economic models are often faced with two pain points. The first problem is that the loss function typically encodes a diverse set of equilibrium conditions, such as market clearing and households' or firms' optimality conditions. Hence the training algorithm trades off errors between those -- potentially very different -- equilibrium conditions. This renders the interpretation of the remaining errors challenging. The second problem is that portfolio choice in models with multiple assets is only pinned down for low errors in the corresponding equilibrium conditions. In the beginning of training, this can lead to fluctuating policies for different assets, which hampers the training process. To alleviate these issues, we propose two complementary innovations. First, we introduce Market Clearing Layers, a neural network architecture that automatically enforces all the market clearing conditions and borrowing constraints in the economy. Encoding economic constraints into the neural network architecture reduces the number of terms in the loss function and enhances the interpretability of the remaining equilibrium errors. Furthermore, we present a homotopy algorithm for solving portfolio choice problems with multiple assets, which ameliorates numerical instabilities arising in the context of deep learning. To illustrate our method we solve an overlapping generations model with two permanent risk aversion types, three distinct assets, and aggregate shocks.

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。

↑