Posterior Distribution-assisted Evolutionary Dynamic Optimization as an Online Calibrator for Complex Social Simulations

2026-01-27

AI Summary

This work proposes a novel approach that integrates Bayesian posterior modeling with Evolutionary Dynamic Optimization (EDO) to address the challenge of continuously calibrating parameters in complex social system simulators to align with real-time observational data. By learning the posterior distribution of parameters conditioned on observed data and incorporating both pre-training and online fine-tuning mechanisms, the method introduces posterior information into the EDO framework for the first time, substantially enhancing the algorithm’s awareness of and adaptability to dynamic environments. Experimental results on economic and financial simulators demonstrate that the proposed approach significantly improves optimization performance and stability in representative dynamic calibration tasks, thereby extending the applicability boundaries of conventional EDO methods.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Economics, Online Markets and Human Computation: Social networks and social learning
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

The calibration of simulators for complex social systems aims to identify the optimal parameter that drives the output of the simulator best matching the target data observed from the system. As many social systems may change internally over time, calibration naturally becomes an online task, requiring parameters to be updated continuously to maintain the simulator's fidelity. In this work, the online setting is first formulated as a dynamic optimization problem (DOP), requiring the search for a sequence of optimal parameters that fit the simulator to real system changes. However, in contrast to traditional DOP formulations, online calibration explicitly incorporates the observational data as the driver of environmental dynamics. Due to this fundamental difference, existing Evolutionary Dynamic Optimization (EDO) methods, despite being extensively studied for black-box DOPs, are ill-equipped to handle such a scenario. As a result, online calibration problems constitute a new set of challenging DOPs. Here, we propose to explicitly learn the posterior distributions of the parameters and the observational data, thereby facilitating both change detection and environmental adaptation of existing EDOs for this scenario. We thus present a pretrained posterior model for implementation, and fine-tune it during the optimization. Extensive tests on both economic and financial simulators verify that the posterior distribution strongly promotes EDOs in such DOPs widely existed in social science.

Problem

• online calibration
• dynamic optimization
• social simulation
• parameter adaptation
• evolutionary optimization

Innovation

• Posterior Distribution
• Evolutionary Dynamic Optimization
• Online Calibration
• Dynamic Optimization Problem
• Social Simulation