TABLE OF CONTENTS Rong Chen
Department of Information and Decision Sciences
University of Illinois at Chicago
Chicago, Illinois 60607
U.S.A.
E-mail: rongchen@uic.edu
The sequential Monte Carlo (SMC) methodology is a family of Monte Carlo methods that processes information sequentially. It has shown to be able to solve a large class of highly complex inference and optimization problems that can be formulated as stochastic dynamic systems. By recursively generating random samples of the state variables of the dynamic systems, SMC adapts flexibly to the dynamics of the underlying stochastic systems. It opens up new frontiers for cross-fertilization between statistical science and many application areas.
In this note, we present an overview of SMC, its applications and some recent developments. Specifically, we introduce a general framework of SMC, and discuss various strategies on fine-tuning the different components in the SMC framework in order to achieve maximum efficiency. SMC applications, specially those in science, engineering, bioinformatics and financial data analysis are discussed.
Stochastic systems are routinely encountered in science, engineering and economics. Many of these systems have a natural dynamic structure; others can often be viewed dynamically. For example, digital communication signals are received sequentially in time; objects move continuously in time in a tracking task; polymers are built-up by adding one monomer at a time; and a contingency table can be filled-up one column at a time. Proper statistical analysis which takes into consideration of the dynamic nature of the systems has significant impacts on a wide range of important applications. However,...
