Neural Attention in Heterogeneous-Agent Economies
Alessandro Villa
Additional contact information
Alessandro Villa: https://www.chicagofed.org/people/v/villa-alessandro
No WP 2026-14, Working Paper Series from Federal Reserve Bank of Chicago
Abstract:
Transformers, the core architecture behind modern large language models, combine flexible nonlinear approximation with attention, a mechanism that learns how information is aggregated across inputs. Can attention reveal which parts of an agent distribution matter for aggregate dynamics? I represent cross-sectional distributions as economic tokens and embed a transformer in a recursive Krusell–Smith-style solution method. The transformer forecasts the continuation distribution entering individual Bellman equations. I establish an analytical link between transformer attention and the sensitivity of aggregate policy functions to distributional components, with attention recovering their normalized marginal sensitivities under a restricted representation. In Krusell–Smith benchmarks, the transformer rediscovers approximate aggregation and assigns nearly uniform attention when aggregate capital is nearly sufficient. In a heterogeneous-firm economy with endogenous default, attention concentrates near the firm default margin and becomes state dependent: during downturns attention shifts toward financially fragile firms, whose balance sheets become more consequential for leverage and aggregate dynamics.
Keywords: heterogeneous-agent economies; heterogeneous firms; firm dynamics; financial frictions; endogenous default; transformer attention; computational economics; distributional dynamics; neural networks; machine learning (search for similar items in EconPapers)
JEL-codes: C45 C63 C68 D22 E21 E32 E44 G33 (search for similar items in EconPapers)
Pages: 77 pages
Date: 2026-08-19
References: Add references at CitEc
Citations:
Downloads: (external link)
https://doi.org/10.21033/wp-2026-14 Persistent link (text/html)
https://www.chicagofed.org/-/media/publications/wo ... s/2026/wp2026-14.pdf Full text (application/pdf)
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:fip:fedhwp:104142
Ordering information: This working paper can be ordered from
DOI: 10.21033/wp-2026-14
Access Statistics for this paper
More papers in Working Paper Series from Federal Reserve Bank of Chicago Contact information at EDIRC.
Bibliographic data for series maintained by Lauren Wiese ().