Professor Jin Jiashun, Chief Professor of Southeast University, Dean of the School of Statistics and Data Science. He received his Ph.D. in Statistics from Stanford University in 2003. His research focuses on statistical inference for big data, with particular expertise in tackling extremely challenging scenarios involving sparse and weak signals (Rare and Weak).

Professor Jin's early research centered on large-scale multiple testing problems, dedicated to developing (Tukey's) Higher Criticism (HC) and practical False Discovery Rate (FDR) control methods. He expanded the HC method into a systematic toolkit that precisely characterizes the phase transition phenomenon of sparse and weak signals. This work has been successfully applied to key problems in genetics, genomics, cosmology, and astronomy, including cancer classification, cancer cluster analysis, and the detection of non-Gaussian signals in Cosmic Microwave Background (CMB) radiation.

More recently, he has shifted his focus to complex graph structures, social networks, sparse Principal Component Analysis (PCA), and random matrix theory. He has successively proposed several groundbreaking methods: Graphlet Screening (GS) for high-dimensional variable selection; the innovated Hidden Factor-adjusted PCA (IF-PCA) for dimension reduction and high-dimensional clustering; and the Spectral Clustering On Ratios-of-Eigenvectors (SCORE) method for community detection in networks.

Professor Jin also led his team in systematically compiling and organizing the MADStat (Multi-Attribute Dataset of Statistics) dataset—a comprehensive collection of collaboration networks and citation networks among statisticians. This dataset encompasses text and citation data from 83,331 papers published in 36 statistical journals between 1975 and 2015. It stands as the first large-scale, multi-attribute, high-quality modern dataset on statistical literature, providing a valuable resource for the fields of statistics and machine learning. Based on the MADStat dataset, the team designed the now well-known statistical triangle, which perfectly corroborates the simplicial structure within the spectral space of non-negative matrices.