Bagged Filters for Partially Observed Interacting Systems

• 成果类型: Article
• 署名作者: Ionides, Edward L.; Asfaw, Kidus; Park, Joonha; King, Aaron A.
• 署名单位: University of Michigan System; University of Michigan; University of Kansas; University of Michigan System; University of Michigan; University of Michigan System; University of Michigan
• 刊物名称: JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
• ISSN/ISSBN: 0162-1459
• DOI: 10.1080/01621459.2021.1974867
• 发表日期: 2023
• 页码: 1078-1089
• 关键词: time-series analysis; disease dynamics; particle filter; monte-carlo; ensemble; inference; measles; models; bounds

摘要

Bagging (i.e., bootstrap aggregating) involves combining an ensemble of bootstrap estimators. We consider bagging for inference from noisy or incomplete measurements on a collection of interacting stochastic dynamic systems. Each system is called a unit, and each unit is associated with a spatial location. A motivating example arises in epidemiology, where each unit is a city: the majority of transmission occurs within a city, with smaller yet epidemiologically important interactions arising from disease transmission between cities. Monte Carlo filtering methods used for inference on nonlinear non-Gaussian systems can suffer from a curse of dimensionality (COD) as the number of units increases. We introduce bagged filter (BF) methodology which combines an ensemble of Monte Carlo filters, using spatiotemporally localized weights to select successful filters at each unit and time. We obtain conditions under which likelihood evaluation using a BF algorithm can beat a COD, and we demonstrate applicability even when these conditions do not hold. BF can out-perform an ensemble Kalman filter on a coupled population dynamics model describing infectious disease transmission. A block particle filter (BPF) also performs well on this task, though the bagged filter respects smoothness and conservation laws that a BPF can violate. for this article are available online.