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 con...
| 主要な著者: | , , , , , , |
|---|---|
| フォーマット: | Conference item |
| 言語: | English |
| 出版事項: |
Association for Computing Machinery
2023
|
| _version_ | 1826312711017857024 |
|---|---|
| author | Chopra, A Rodríguez, A Subramanian, J Quera-Bofarull, A Krishnamurthy, B Aditya Prakash, B Raskar, R |
| author_facet | Chopra, A Rodríguez, A Subramanian, J Quera-Bofarull, A Krishnamurthy, B Aditya Prakash, B Raskar, R |
| author_sort | Chopra, A |
| collection | OXFORD |
| description | 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 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. |
| first_indexed | 2024-04-23T08:24:49Z |
| format | Conference item |
| id | oxford-uuid:e883b52f-76d2-4e93-85d7-c0115e260f5c |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-04-23T08:24:49Z |
| publishDate | 2023 |
| publisher | Association for Computing Machinery |
| record_format | dspace |
| spelling | oxford-uuid:e883b52f-76d2-4e93-85d7-c0115e260f5c2024-04-09T12:17:27ZDifferentiable agent-based epidemiologyConference itemhttp://purl.org/coar/resource_type/c_5794uuid:e883b52f-76d2-4e93-85d7-c0115e260f5cEnglishSymplectic ElementsAssociation for Computing Machinery2023Chopra, ARodríguez, ASubramanian, JQuera-Bofarull, AKrishnamurthy, BAditya Prakash, BRaskar, RMechanistic 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 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. |
| spellingShingle | Chopra, A Rodríguez, A Subramanian, J Quera-Bofarull, A Krishnamurthy, B Aditya Prakash, B Raskar, R Differentiable agent-based epidemiology |
| title | Differentiable agent-based epidemiology |
| title_full | Differentiable agent-based epidemiology |
| title_fullStr | Differentiable agent-based epidemiology |
| title_full_unstemmed | Differentiable agent-based epidemiology |
| title_short | Differentiable agent-based epidemiology |
| title_sort | differentiable agent based epidemiology |
| work_keys_str_mv | AT chopraa differentiableagentbasedepidemiology AT rodrigueza differentiableagentbasedepidemiology AT subramanianj differentiableagentbasedepidemiology AT querabofarulla differentiableagentbasedepidemiology AT krishnamurthyb differentiableagentbasedepidemiology AT adityaprakashb differentiableagentbasedepidemiology AT raskarr differentiableagentbasedepidemiology |