Networks provide a fundamental representation of complex systems across the social and natural sciences, from friendships to metabolic interactions, and it is therefore critical that we develop principled, scalable, and interpretable statistical models and inference algorithms to summarize the structure and dynamics of network data. In this talk I’ll give an overview of two recent projects developing new efficient statistical inference algorithms for complex network data. First, I will describe a belief propagation algorithm for computing one-point marginals and other quantities of interest in probabilistic graphical models on networks with short loops, which provides a significant accuracy improvement over standard belief propagation on highly clustered networks and runs in only a fraction of the time it takes to run standard Monte Carlo sampling. I will then move on to discuss a fast parameter-free algorithm motivated by information theoretic arguments to perform spatially contiguous clustering of areal units with distributional metadata such as those sampled for census analysis. I will illustrate how this method is capable of recovering planted spatial clusters in noisy synthetic data and that it can meaningfully coarse-grain real demographic data to provide new insights about urban spatial segregation.”

“Alec Kirkley is an Assistant Professor jointly appointed in the Institute of Data Science and Department of Urban Planning and Design at the University of Hong Kong. He obtained his PhD in physics at the University of Michigan and did his undergraduate studies at the University of Rochester. His research focuses on the theory of complex networks and the statistical physics of urban systems, with specific interests involving the characterization of structure in networks with metadata, the development of analysis methods and algorithms for statistical inference with network data, the structure and dynamics of human mobility, and the spatial manifestation of socioeconomic inequality. His research involves a balance of mathematical theory, computer simulation, and analysis of empirical data. His overarching goal is to develop physics-inspired mathematical and computational methods to aid in the understanding and modeling of complex networks and urban systems.”