The Practicality of Normalizing Flow Test-Time Training in Bayesian Inference for Agent-Based Models
This work addresses the challenge of robust Bayesian inference for ABMs in economics and social science, though it appears incremental as it applies existing TTT concepts to a new domain.
The paper tackles the problem of adapting normalizing flow models to distribution shifts in agent-based models (ABMs) by proposing test-time training (TTT) strategies, demonstrating that these schemes enable real-time adjustment and are remarkably effective for parameter inference.
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.