Quera-Bofarull, A., Chopra, A., Aylett-Bullock, J., Cuesta-Lazaro, C., Calinescu, A., Raskar, R., & Wooldridge, M. (2023). Don’t simulate twice: One-shot sensitivity analyses via automatic differentiation. Proceedings of Autonomous Agents and Multi-agent Systems (AAMAS 2023)

Abstract

Agent-based models (ABMs) are a promising tool to simulate complex environments. Their rapid adoption requires scalable specification, efficient data-driven calibration, and validation through sensitivity analyses. Recent progress in tensorized and differentiable ABM design (GradABM) has enabled fast calibration of million-size populations, however, validation through sensitivity analysis is still computationally prohibitive due to the need for running the model a large number of times. Here, we present a novel methodology that uses automatic differentiation to perform a sensitivity analysis on a calibrated ABM without requiring any further simulations. The key insight is to leverage gradients of a GradABM to compute exact partial derivatives of any model output with respect to an arbitrary combination of parameters. We demonstrate the benefits of this approach on a case study of the first wave of COVID-19 in London, where we investigate the causes of variations in infections by age, socio-economic index, ethnicity, and geography. Finally, we also show that the same methodology allows for the design of optimal policy interventions.