Differentiable Agent-based Epidemiology
Mechanistic simulators are an indispensable tool for epidemiology to explore the behavior of complex, dynamic infections under varying conditions and navigate uncertain environments. Agent-based models (ABMs) are an increasingly popular simulation paradigm that can represent the heterogeneity of contact interactions with granular detail and agency of individual behavior. However, conventional ABM frameworks are not differentiable and present challenges in scalability; due to which it is non-trivial to connect them to auxiliary data sources. In this paper, we introduce GradABM: a scalable, differentiable design for agent-based modeling that is amenable to gradient-based learning with automatic differentiation. GradABM can quickly simulate million-size populations in few seconds on commodity hardware, integrate with deep neural networks and ingest heterogeneous data sources. This provides an array of practical benefits for calibration, forecasting, and evaluating policy interventions. We demonstrate the efficacy of GradABM via extensive experiments with real COVID-19 and influenza datasets.
Code (1)
Tasks
EpidemiologyNavigateSimilar Papers 제목 키워드 기반
Information Theory Unification of Epidemiological and Population Dynamics
We reformulate models in epidemiology and population dynamics in terms of probability distributions. This allows us to construct the Fisher information, which we interpret as the metric of a one-dimensional differentiabl…
EpidemiologyBehavioral epidemiology: An economic model to evaluate optimal policy in the midst of a pandemic
This paper combines a canonical epidemiology model of disease dynamics with government policy of lockdown and testing, and agents' decision to social distance in order to avoid getting infected. The model is calibrated w…
EpidemiologyWhy can't Epidemiology be automated (yet)?
Recent advances in artificial intelligence (AI) - particularly generative AI - present new opportunities to accelerate, or even automate, epidemiological research. Unlike disciplines based on physical experimentation, a …
Thought Viruses and Asset Prices
We use insights from epidemiology, namely the SIR model, to study how agents infect each other with "investment ideas." Once an investment idea "goes viral," equilibrium prices exhibit the typical "fever peak," which is …
EpidemiologySpatio-temporal data mining in ecological and veterinary epidemiology
Understanding the spread of any disease is a highly complex and interdisciplinary exercise as biological, social, geographic, economic, and medical factors may shape the way a disease moves through a population and optio…
Epidemiology