Automatic Differentiation of Agent-Based Models

2025-09-03

AI Summary

Agent-based models (ABMs) face computational bottlenecks—high runtime costs and intractable parameter calibration—due to complex agent interactions and high-dimensional parameter spaces, limiting their applicability in complex systems research. This paper introduces automatic differentiation (AD) systematically into ABM frameworks for the first time, enabling end-to-end differentiable modeling of large-scale agent systems. The approach supports efficient gradient-based parameter calibration and sensitivity analysis, and extends the applicability of variational inference to ABMs. Evaluated on three canonical ABMs—the Axtell firm model, Sugarscape, and the SIR epidemic model—the method reduces computational overhead significantly and accelerates calibration by one to two orders of magnitude, while preserving full model semantics. Its core contribution is the establishment of the first general-purpose, scalable differentiable ABM paradigm, offering a new pathway for complex systems modeling that jointly ensures interpretability and computational efficiency.

Technology Category

• Multiagent Systems: Adversarial Agents
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• 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

Agent-based models (ABMs) simulate complex systems by capturing the bottom-up interactions of individual agents comprising the system. Many complex systems of interest, such as epidemics or financial markets, involve thousands or even millions of agents. Consequently, ABMs often become computationally demanding and rely on the calibration of numerous free parameters, which has significantly hindered their widespread adoption. In this paper, we demonstrate that automatic differentiation (AD) techniques can effectively alleviate these computational burdens. By applying AD to ABMs, the gradients of the simulator become readily available, greatly facilitating essential tasks such as calibration and sensitivity analysis. Specifically, we show how AD enables variational inference (VI) techniques for efficient parameter calibration. Our experiments demonstrate substantial performance improvements and computational savings using VI on three prominent ABMs: Axtell's model of firms; Sugarscape; and the SIR epidemiological model. Our approach thus significantly enhances the practicality and scalability of ABMs for studying complex systems.

Problem

• Reducing computational demands of agent-based models
• Enabling efficient calibration of numerous parameters
• Facilitating gradient-based sensitivity analysis and inference

Innovation

• Automatic differentiation for agent-based models
• Gradients enable efficient calibration and analysis
• Variational inference for scalable parameter optimization