The Practicality of Normalizing Flow Test-Time Training in Bayesian Inference for Agent-Based Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Junyao, Li, Jinglai, Tang, Junqi
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