Variational Inference with Agent-Based Models

In this paper, we develop a variational method to track and make predictions about a real-world system from continuous imperfect observations about this system, using an agent-based model that describes the system dynamics. By combining the power of big data with the power of modelthinking in the stochastic process framework, we can make many valuable predictions. We show how to track the spread of an epidemic at the individual level and how to make shortterm predictions about traffic congestion. This method points to a new way to bring together modelers and data miners by turning the real world into a living lab.

Authors

• Wen Dong Key Laboratory of Social Computing and Cognitive Intelligence, Dalian University of Technology

Keywords

• Social simulation
• interactive simulation
• novel agent and multi-agent applications
• epidemic dynamics
• short term traffic forecasting
• discrete event simulation
• stochastic kinetic model
• variational methods
• expectation propagation
• Bethe variational principle
• Markov process