Recent Publication
Deep Surrogates for Finance
Deep learning surrogates for high-dimensional option pricing, published in the Journal of Financial Economics (2026).
Research
My research lies at the intersection of computational macroeconomics, finance, and artificial intelligence. I build deep learning methods and scalable numerical frameworks for solving high-dimensional dynamic models that were long considered computationally intractable. These tools allow richer quantitative analysis of climate policy, macro-finance, dynamic contracting, and asset pricing.
My work has appeared in outlets including Econometrica, the Review of Economic Studies, the Journal of Financial Economics, the Economic Journal, and the Annual Review of Economics.
Featured Work
Current Project
Optimal Carbon Tax Rules
Machine learning methods for computing constrained carbon tax policies in high-dimensional climate-economy models.
Open Research Software
The Climate in Climate Economics
Open-source code for modern climate emulation and integrated assessment work in economics.
News
Summer 2026
Co-organizing AI for Economics and Finance Summer School/Conference at the University of Turin (August 24–28, 2026). Deadline: Apr 30
June–July 2026
Keynote at the 32nd International Conference Computing in Economics and Finance (June 29–July 1, 2026, Venice).
July 2026
Teaching at the PKU-Zurich PhD Summer School on Machine Learning for Macroeconomics and Finance (July 6–10, 2026, Beijing).
2026
Teaching mini-course on solving integrated assessment models via deep learning at CEMRACS2026.
November 2025
Machine Learning for Dynamic Incentive Problems (with P. Renner) conditionally accepted at Review of Economic Studies. Accepted