(Virtual) Seminar Series | High-dimensional Parameter Learning over General Graphical State Space Models: Beating the Curse of Dimensionality

Ning Ning, Postdoctoral Research Fellow

Department of Statistics, University of Michigan, Ann Arbor

Disease transmission systems are highly nonlinear and stochastic and are imperfectly observable. However, conducting high-dimensional parameter learning for partially observed, nonlinear, and stochastic spatiotemporal processes is a methodological challenge and is an open problem so far. We propose the iterated block particle filter (IBPF) algorithm for learning high-dimensional parameters over graphical state space models with general state spaces, measures, transition densities, and graph structure. Theoretical performance guarantees are obtained on beating the curse of dimensionality (COD), algorithm convergence, and likelihood maximization. Experiments on a highly nonlinear and non-Gaussian spatiotemporal model for measles transmission reveal that the iterated ensemble Kalman filter algorithm (Li et al. (2020), Science) is ineffective and the iterated filtering algorithm (Ionides et al. (2015), PNAS) suffers from the COD, while our IBPF algorithm beats COD consistently across various experiments with different metrics.

Talk based on paper: "Iterated Block Particle Filter for High-dimensional Parameter Learning: Beating the Curse of Dimensionality'', Ning Ning and Edward Ionides, ArXiv: https://arxiv.org/abs/2110.10745, 2021.

Ning Ning is currently a Postdoctoral Research Fellow in the Dept. of Statistics at the University of Michigan, Ann Arbor. Her research interests are data science, Markov chains, time series, networks, and machine learning. She received her PhD in Statistics and Applied Probability at UCSB. Prior to joining University of Michigan, she was holding a position as Postdoctoral Research Associate in the Dept. of Applied Math at the Univ. of Washington, Seattle. Her personal website is https://sites.google.com/site/patricianing/.