A differentiable model of supply-chain shocks
Not on the map. Why?
Abstract (arXiv)
Modelling how shocks propagate in supply chains is an increasingly important challenge in economics. Its relevance has been highlighted in recent years by events such as Covid-19 and the Russian invasion of Ukraine. Agent-based models (ABMs) are a promising approach for this problem. However, calibrating them is hard. We show empirically that it is possible to achieve speed ups of over 3 orders of magnitude when calibrating ABMs of supply networks by running them on GPUs and using automatic differentiation, compared to non-differentiable baselines. This opens the door to scaling ABMs to model the whole global supply network.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 6 of its 24 references that are in the map. First posted on arXiv 7 Nov 2025.
Builds on
6 of 24 references.
References · 6
- 2019Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyrocited by 191
- 2024sbi reloaded: a toolkit for simulation-based inference workflowscited by 23
- 2022Differentiable Agent-based Epidemiologycited by 21
- 2022On learning agent-based models from datacited by 14
- 2025Learning Individual Behavior in Agent-Based Models with Graph Diffusion Networkscited by 4
- 2025Automatic Differentiation of Agent-Based Modelscited by 4
Built on by
Not cited yet.