PEM-SMC: An algorithm for optimizing model parameters
Year: 2024
Type: article
Abstract: Bayesian inference is crucial for optimizing parameters in complex models, but often requires sampling due to high-dimensional, intractable posteriors. Beyond Markov-Chain Monte Carlo (MCMC) methods, Sequential Monte Carlo (SMC) algorithms offer an alternative. This paper introduces a Matlab toolbox for the Particle Evolution Metropolis Sequential Monte Carlo (PEM-SMC) algorithm, which combines the strengths of population-based MCMC and SMC. Two case studies – a complex multi-modal probability and a land surface model – demonstrate the toolbox’s capabilities. This tool is valuable for Bayesian inference across fields like statistics, ecology, hydrology, and land surface processes. • The PEM-SMC algorithm is developed for improving sampling diversity and efficiency. • A MATLAB toolbox is developed to broaden the PEM-SMC algorithm’s accessibility. • Practical applications of PEM-SMC are showcased through case studies.
Source: Software Impacts
Authors: Gaofeng Zhu, Qiang Chen, Xiangyu Yu, Cong Xu, Kun Zhang, Yunquan Wang, Wei Gong, Tao Che
Institutions: Lanzhou University, Tianjin University of Finance and Economics, Sun Yat-sen University, China University of Geosciences, Beijing Normal University, State Key Laboratory of Earth Surface Processes and Resource Ecology, Chinese Academy of Sciences, Northwest Institute of Eco-Environment and Resources
Language: English
Subfield: Statistics and Probability
Field: Mathematics
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $480
Awards: G3945201014, G6333443549, G7246649586
OpenAlex ID: W4405364805