On April 23, 2025, at the invitation of the School of Management, Dr. Xun Xiao, Lecturer in the Department of Mathematics and Statistics at the University of Otago, New Zealand, and Dr. Mimi Zhang, Assistant Professor in the School of Computer Science and Statistics at Trinity College Dublin, Ireland, respectively delivered academic lectures titled "A Practical Guide to the Data Universe: Finding Statistical Evidence Amidst Chaos" and "Parallel Adaptive Reliability Analysis Based on Penalized Learning Functions" in Lecture Hall 214. This event marked the 5th session of the 2025 Overseas Lecture Series hosted by the School of Management. Chaired by Associate Professor Chenglong Li, it was attended by young faculty members and graduate students from the school.

Prior to the lectures, Associate Professor Li Chenglong briefly introduced Dr. Xiao Xun and Dr. Zhang Mimi's backgrounds and academic achievements, and extended a warm welcome to them. In his lecture, Dr. Xiao Xun focused on the modeling and identification of primary and cascading failures in pipeline systems. Addressing the challenges in this field, he explained that the study introduced a multivariate Hawkes process to construct a network failure framework. By integrating the physical characteristics of pipelines with failure time series, the research quantifies the probability of adjacent pipelines experiencing secondary failures due to the impact of primary failures in the short term. Additionally, he conducted inferences using the EM algorithm and likelihood estimation, and verified the effectiveness of this method in identifying and predicting cascading failures through real-world data validation.

Dr. Zhang Mimi's lecture centered on the parallelized analysis of structural reliability. This research focuses on probabilistic methods for evaluating the safety of structures under uncertain conditions, with primary applications in civil engineering, mechanical engineering, and aerospace structures. Dr. Zhang shared in detail the Bayesian learning framework, parallel adaptive reliability analysis based on penalized learning functions, and her latest research on functional data.

The lectures delivered by the two scholars were rich in content and profound in analysis, greatly benefiting the faculty and students present. At the conclusion of the lectures, the two experts engaged in extensive interactive exchanges with the audience, patiently answering questions raised by the participants, creating a lively atmosphere.

[Written by Gao Haoran & Zhang Jinkai; Reviewed by Shao Jing & Zhang Shuang]

[Lecturers' Biographies]

Dr. Xun Xiao is a Lecturer in the Department of Mathematics and Statistics at the University of Otago, New Zealand. He holds a Bachelor of Science in Statistics from the University of Science and Technology of China and a PhD in Systems Engineering and Engineering Management from City University of Hong Kong. His research interests include multivariate point process modeling, quality control in industrial settings, and system reliability optimization. He has published numerous papers in prominent international academic journals such as Technometrics, Journal of the Royal Statistical Society, Series C, Journal of Quality Technology, and IEEE Transactions on Reliability. He is the recipient of the Worsley Early Career Award presented by the New Zealand Statistical Association.

Dr. Mimi Zhang is an Assistant Professor in the School of Computer Science and Statistics at Trinity College Dublin, Ireland. She obtained a Bachelor of Science in Statistics from the University of Science and Technology of China and a PhD in Industrial Engineering from City University of Hong Kong. She previously served as a Research Assistant at the University of Strathclyde and Imperial College London. Her main research focuses on the intersection of machine learning and operations research, covering cluster analysis, Bayesian optimization, functional data analysis, and reliability engineering. She has extensive experience in processing multivariate, functional, and image data. Her research findings have been published in over 30 top-tier journals and conferences, including IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), International Conference on Machine Learning (ICML), and European Journal of Operational Research (EJOR).