The Practicality of Normalizing Flow Test-Time Training in Bayesian Inference for Agent-Based Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912818032279552 |
|---|---|
| author | Zhang, Junyao Li, Jinglai Tang, Junqi |
| author_facet | Zhang, Junyao Li, Jinglai Tang, Junqi |
| contents | Agent-Based Models (ABMs) are gaining great popularity in economics and social science because of their strong flexibility to describe the realistic and heterogeneous decisions and interaction rules between individual agents. In this work, we investigate for the first time the practicality of test-time training (TTT) of deep models such as normalizing flows, in the parameters posterior estimations of ABMs. We propose several practical TTT strategies for fine-tuning the normalizing flow against distribution shifts. Our numerical study demonstrates that TTT schemes are remarkably effective, enabling real-time adjustment of flow-based inference for ABM parameters. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_07413 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | The Practicality of Normalizing Flow Test-Time Training in Bayesian Inference for Agent-Based Models Zhang, Junyao Li, Jinglai Tang, Junqi Machine Learning Multiagent Systems Agent-Based Models (ABMs) are gaining great popularity in economics and social science because of their strong flexibility to describe the realistic and heterogeneous decisions and interaction rules between individual agents. In this work, we investigate for the first time the practicality of test-time training (TTT) of deep models such as normalizing flows, in the parameters posterior estimations of ABMs. We propose several practical TTT strategies for fine-tuning the normalizing flow against distribution shifts. Our numerical study demonstrates that TTT schemes are remarkably effective, enabling real-time adjustment of flow-based inference for ABM parameters. |
| title | The Practicality of Normalizing Flow Test-Time Training in Bayesian Inference for Agent-Based Models |
| topic | Machine Learning Multiagent Systems |
| url | https://arxiv.org/abs/2601.07413 |