Optimal Trade and Industrial Policies in the Global Economy: A Deep Learning Framework
This work addresses policy-making challenges in international economics by providing a computational tool for analyzing sectoral heterogeneity and policy interactions, though it is incremental in applying deep learning to existing economic models.
The paper tackled the problem of determining optimal trade and industrial policies in global economies by developing a deep learning framework, DL-opt, which solved for non-cooperative tariffs and subsidies across 7 economies and 44 sectors, revealing that global dual competition leads to lower tariffs and higher welfare compared to tariff wars.
We propose a deep learning framework, DL-opt, designed to efficiently solve for optimal policies in quantifiable general equilibrium trade models. DL-opt integrates (i) a nested fixed point (NFXP) formulation of the optimization problem, (ii) automatic implicit differentiation to enhance gradient descent for solving unilateral optimal policies, and (iii) a best-response dynamics approach for finding Nash equilibria. Utilizing DL-opt, we solve for non-cooperative tariffs and industrial subsidies across 7 economies and 44 sectors, incorporating sectoral external economies of scale. Our quantitative analysis reveals significant sectoral heterogeneity in Nash policies: Nash industrial subsidies increase with scale elasticities, whereas Nash tariffs decrease with trade elasticities. Moreover, we show that global dual competition, involving both tariffs and industrial subsidies, results in lower tariffs and higher welfare outcomes compared to a global tariff war. These findings highlight the importance of considering sectoral heterogeneity and policy combinations in understanding global economic competition.