SDS Colloquium SeriesTopicWhen Strategic Customers Meet Strategic Servers: Individual and Social Optimization in Many-Server Queueing SystemsSpeakerAmy R. Ward, Rothman Family Professor, Operations Management, University of Chicago Booth School of BusinessHostXinyun CHEN, Associate Professor, School of Data Science, CUHK-ShenzhenDateJanuary 16 (Friday), 2025Time2:30 PM - 3:30 PM, Beijing TimeFormatHybridVenueRoom 103, Dao Yuan BuildingZoom Linkhttps://cuhk-edu-cn.zoom.us/j/99435616036?pwd=bvgndmtjefy4uFeREjLlv6bbe4tNHu.1Meeting ID: 994 3561 6036 Passcode: 20260116LanguageEnglishAbstractWe initiate the study of joint strategic behavior of customers and servers in many-server queueing systems. We model customers as strategic agents who decide whether to join the system by weighing reward from service against cost of waiting, following the seminal works of Naor (1969) and Knudsen (1972). In those works, customers use a threshold equilibrium joining strategy based on the number of…

SDS Colloquium SeriesTopicCointegration of Two Intrinsically Stationary Spatial ProcessesSpeakerQiwei YAO, Professor, Department of Statistics, London School of Economics and Political ScienceHostJianfeng YAO, Presidential Chair Professor, Area Head - Statistics, School of Data Science, CUHK-ShenzhenDateJanuary 15 (Thursday), 2025Time4:00 PM - 5:00 PM, Beijing TimeFormatOnsiteVenueRoom 103, Dao Yuan BuildingLanguageChineseAbstractThe concept of the intrinsic processes proposed by Matheron (1973) provides an elegant mathematical framework for modeling nonstationary spatial phenomena. It can be viewed as a direct analogue of taking differences of nonstationary time series in order to achieve stationarity. But it is applicable to spatial data observed on both regular and irregular grids.The goal of this paper is to establish the inference methods and the relevant theory for identifying the cointegration between two simple intrinsic processes. We apply the least squares estimation,…

The School of Data Science (SDS) Capstone Project is designed to provide SDS and the Financial Engineering (FE) junior and senior students with the opportunity to apply the knowledge and skills they have acquired to real-world projects. Students will work in teams with their peers under the guidance of both a practitioner supervisor and a professor supervisor.For AY2025-26 Term 2, 15 partner companies will offer a total of 48 projects for students to choose from. Students who are interested in this course are warmly welcomed to participate in the Capstone Project Pitch Day.Details of the EventDate and TimeDec 6, 2025 9:00 - 12:30VenueRoom 103, Dao Yuan BuildingLanguageThe primary language of this event is ChineseProgram Outline▪️ 9:00 - 9:15 Opening▪️ 9:15 - 11:45 Capstone Projects Introduction▪️ 11:45 - 12:30 Free DiscussionsPartner EntitiesThanks to the partner entities for AY2025-26:* Listed in alphabetical order Applied Artificial Intelligence Laboratory (HK)…

The Guangdong Provincial Engineering Technology Research Center of Generalized Human body Information Perception and Pattern Analysis aims to study the original cutting-edge technologies of generalized perception and pattern analysis, and promote the development of Guangdong Province in the field of related technology applications. As a key sub-topic of artificial intelligence, generalized perception and pattern analysis of body surface is a key pillar for enabling the future and realizing the implementation of artificial intelligence in the fields of big health, security, and intelligent manufacturing. The center will combine new-generation information technologies such as artificial intelligence and big data, and take the needs of new-generation feature recognition and Traditional Chinese Medicine intelligent medical diagnosis as the main guideline, to carry out extensive research on biometric feature recognition, promote the construction of a feature information standard database,…

SDS Colloquium SeriesTopic 预测赋能的最优样本选择Speaker 邹长亮，南开大学统计与数据科学学院教授Host吴建福，香港中文大学（深圳）数据科学学院校长学勤讲座教授Date 2025年11月27日（周四）Time 下午4:00 – 5:00 ，北京时间Format 现场Venue 道远楼103会议室Language 中文Abstract 在大数据时代，我们常需要从海量数据中挑选出最具信息量的个体。传统样本选择方法多关注使得既定模型尽可能估计好的的代表性样本子集。但在半监督环境下，我们往往只有少量的已标注数据，而目标是如何从大量未标注数据中挑选出由其“未观测响应”所决定的最有价值的样本。本报告首先将样本选择问题重构为一个共形化多重检验问题。我们提出一个以数据最大化利用为核心的统一框架：充分利用标注和未标注数据，通过全排列构建得分并校准共形p值，从而在有限样本下控制错误选择率的同时显著提升监测效率。 随后，我们讨论在资源受限或需保持多样性时的最优样本选择。基于预测推断的不确定度量，我们建立错误选择率可控的优化策略，在有限预算下找到最具潜在价值的多样化样本。我们从理论上证明了其样本选择的渐近最优性，并通过模拟与真实数据验证其在实际应用中的高效性与可靠性。Biography 邹长亮，南开大学统计与数据科学学院教授。主要从事统计学及其与数据科学领域的交叉研究和实际应用。研究兴趣包括：预测性推断、高维数据统计学习、变点和异常点检测等。近年来在统计学和机器学习领域的权威期刊和会议上发表论文五十余篇，入选爱思唯尔“中国高被引学者”。主持基金委优青、杰青、重点项目、重大项目课题和科技部重点研发计划课题等。任教育部科技委委员、全国应用统计专业硕士教学指导委员会委员、中国现场统计研究会副理事长等。

SDS Colloquium SeriesTopicHarmony in Cyber Physical Systems: Systems and Control PerspectivesSpeakerShinji HARA, Professor Emeritus, The University of Tokyo and Tokyo Institute of TechnologyHostJunfeng WU, Associate Professor, School of Data Science, CUHK-ShenzhenTianshi CHEN, Professor, School of Data Science, CUHK-ShenzhenDate18 November (Tuesday), 2025Time11:00 AM - 12:00 PM, Beijing TimeFormatOnsiteVenueRoom 103, Dao Yuan BuildingLanguageEnglishAbstractThere are a lot of world-wide crucial issues such as energy, environment, transportation and so on, and most of the science and engineering communities including the control community should try to solve them by collaborating with each other, where the target physical systems are normally very large and complex. Hence, it is natural from systems and control viewpoints to consider such systems as hierarchically networked dynamical systems, where the purpose of control is to achieve the global tasks by cooperation of multiple…

SDS Colloquium SeriesTopicExtracting Large Machine Learning Models: Theory and PracticeSpeakerHaibo HU, Professor and Associate Head, Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic UniversityHostChenhao MA, Assistant Professor, School of Data Science, CUHK-ShenzhenDate28 November (Friday), 2025Time4:00 PM - 5:00 PM, Beijing TimeFormatHybridVenueRoom 103, Dao Yuan BuildingZoom Linkhttps://cuhk-edu-cn.zoom.us/j/96597538064?pwd=UA4JzmOQBFGpPQOr2xaSaaTNPZ5x1p.1Meeting ID: 965 9753 8064, Password: 154080LanguageEnglishAbstractRecent advancements in machine learning, particularly large language models (LLMs), have revolutionized numerous domains. However, machine learning systems may suffer from model privacy threats known as model extraction (ME) attacks, where an attacker aims to copy the victim model by submitting crafted queries and then using the query-output pairs to train a surrogate model that can emulate the behavior of the victim model. Based on the…

Proposed Admission List Announcement for the Bachelor-Taught Master ProgramIn accordance with the arrangements for the Bachelor-Taught Master Program (hereafter referred to as BTMP), we are announcing the proposed admission list (see attachment). The announcement period is from November 10 to November 17, 2025. If you have any objections to the list, please direct your feedback via email to the BTMP Team during this period. SDS TPG BTMP TeamEmail address: sds_tpgzs@cuhk.edu.cn

Introduction: The Academic Advisory System is a professional team composed of senior professors and staff from the School, dedicated to supporting undergraduates throughout their university experience. It offers guidance on academic planning and provides assistance for students facing academic challenges. Prof. LEE TanAssociate Dean (Undergraduate) & Chair of Student Advising CommitteeWebsite: https://sds.cuhk.edu.cn/en/teacher/2131 Prof. YAN MingDirector of Academic Advising (Computer Science and Engineering)Website: https://sds.cuhk.edu.cn/en/teacher/642 Prof. LIU MengmengDirector of Academic Advising (Computer Science and Engineering)Website: https://sds.cuhk.edu.cn/en/teacher/2239 Prof. CHEN YuangDirector of Academic Advising (Date Science and Big Date Technology)Website: https://sds.cuhk.edu.cn/en/teacher/2078 Prof. MILZAREK AndreDirector of Academic Advising (Date Science and Big Date Technology)Website: https://sds.cuhk.edu.cn/en/teacher/64…

Formulating a Universal Law for Optimal Conversion Efficiency of Quantum ResourcesKey HighlightsSuccessfully proved the Generalized Quantum Stein's Lemma, a significant unsolved problem in quantum information theory.Just as physics has the Second Law of Thermodynamics determining energy conversion efficiency, a similar law was thought to exist for quantum information processing. However, a key component for its formulation, the Generalized Quantum Stein's Lemma, was recently found to have an erroneous existing proof, making it a major unresolved issue.This breakthrough resolves the problem, revealing a universal law that dictates how efficiently resources can be converted for computations and communications in quantum computers. This establishes a unified framework for analyzing the optimal performance of quantum information processing, expected to widely contribute to the analysis and improved design of quantum computing and communication, as well as the advancement of their…

SDS Colloquium SeriesTopicDiversified Bayesian Learning: Optimal Control with Multiple Biased Information SourcesSpeakerJussi KEPPO, Provost's Chair Professor and Head, Department of Analytics & Operations, NUS Business SchoolResearch Director, Institute of Operations Research and Analytics, National University of SingaporeHostZizhuo WANG, Professor & Associate Dean (Education), School of Data Science, CUHK-ShenzhenDate10 November (Monday), 2025Time11:00 AM - 12:00 PM, Beijing TimeFormatHybridVenueRoom 401, Dao Yuan BuildingLive on WeChat ChannelsLanguageEnglishAbstractWe consider a decision-maker (DM) who can acquire signals from multiple biased information sources to learn about a hidden state before making an earning decision. Unbiased signals are also available but come at a higher acquisition cost. The DM jointly optimizes both learning (information acquisition) and earning decisions to minimize expected loss. This problem is motivated by applications such as medical…

SDS Colloquium SeriesTopicBig Spatial Intelligence: From Theory to ApplicationSpeakerRaymond Chi-Wing WONG, Professor, Department of Computer Science and Engineering, The Hong Kong University of Science and TechnologyHostYixiang FANG, Associate Professor, School of Data Science, CUHK-ShenzhenDate15 August (Friday), 2025Time3:30 PM - 4:30 PM, Beijing TimeFormatHybridVenue103 Meeting Room, Dao Yuan BuildingLive on WeChat ChannelsLanguageEnglishAbstractNowadays, location-based services (LBSs), which refer to those services that are based on location (or spatial) data, are broadly used in our daily life. In this talk, we will talk about the recent development of LBSs. Some examples are "Search-nearby", "Spatial Crowdsourcing", "Trace Tracking" and "Shortest Distance". We will focus on presenting some important results about shortest distance queries, one fundamental LBS, in different aspects (e.g., keyword-aware shortest distance queries and stochastic shortest distance queries…

SDS Colloquium SeriesTopicAccelerating Model Training on Ascend Chips: An Industrial System for Profiling, Analysis and OptimizationSpeakerChen TIAN, Professor, School of Computer Science, Nanjing UniversityHostYunming XIAO, Assistant Professor, School of Data Science, CUHK-ShenzhenDate25 August (Monday), 2025Time2:30 PM - 3:30 PM, Beijing TimeFormatHybridVenueRoom 111, Zhi Xin BuildingZoom Linkhttps://cuhk-edu-cn.zoom.us/j/92038677688?pwd=BjHAhAz5m4KnOS9nxiBeggQaBBzvOM.1 Meeting ID: 920 3867 7688 Passcode: 532942LanguageEnglishAbstractTraining large-scale deep learning (DL) models is a resource-intensive and time-consuming endeavor, yet optimizing training efficiency poses significant challenges. The sporadic performance fluctuations during long training require advanced profiling capabilities. It is not easy to perform comprehensive and accurate bottleneck analysis amidst numerous influencing factors. Selecting effective optimization strategies without proper guidance…

Eligibility List of the 2025 BTMT Scheme of School of Data Science The BTMT Admissions Committee of the School of Data Science, The Chinese University of Hong Kong, Shenzhen, hereby announces the eligibility list for the 2025 BTMT Scheme. Public Consultation Period: 5 working days, from September 11 to September 17, 2025 Accommodation for students admitted in the Fall 2026 intake cannot be guaranteed. Room assignments will be made on a first-come, first-served basis, subject to availability. Should there be any objections or inquiries regarding the eligibility list, please submit your feedback by email to sds_ug@cuhk.edu.cn within the designated consultation period. For general inquiries about the BTMT scheme and application procedures, please contact the School of Data Science BTMT Working Group at sds_tpgzs@cuhk.edu.cn. School of Data ScienceThe Chinese University of Hong Kong, ShenzhenSeptember 11, 2025 

Program Overview (Click to view the complete project introduction)CUHK-Shenzhen and Columbia University proudly offer the CUHK-Shenzhen-Columbia Engineering 3+2 Initiative — the only Columbia Engineering Combined Bachelor-Master Arrangement in Asia.Columbia University in the City of New York is a top-tier private research university and one of the fourteen founding members of the Association of American Universities (AAU). It is also a member of the Ivy League. Since 1864, Columbia Engineering has been a resource to the world for major advances in human progress. Today, Columbia Engineering is a global leader in engineering education, research, and impact. Participating Bachelor's Programs at CUHK-Shenzhen:School of Data Science (SDS): All majors, including Data Science and Big Data Technology, Statistics, Computer Science and Engineering, and Financial Engineering (jointly offered by SME/SSE/SDS)Participating Master's Programs at Columbia Engineering:Students can…

DeLiang WANG is a Professor in the School of Data Science, Chinese University of Hong Kong, Shenzhen. From October 1991 to June 2025, he was with the Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences at The Ohio State University, Columbus, OH, where he was a Professor and University Distinguished Scholar. From October 1998 to September 1999, he was a visiting scholar in the Department of Psychology at Harvard University, Cambridge, MA. From October 2006 to June 2007, he was a visiting scholar at Oticon A/S, Copenhagen, Denmark. From October 2014 to December 2014, he was a visiting scholar at Starkey Hearing Technologies, Eden Prairie, MN. From July 1986 to December 1987, he was an Assistant Investigator with the Institute of Computing Technology, Academia Sinica, Beijing.DeLiang WANG received the NSF Research Initiation Award in 1992 and the ONR Young Investigator Award in 1996. He received the Ohio State University College of Engineering…

The School of Data Science (SDS) at The Chinese University of Hong Kong, Shenzhen (CUHK-SZ) aims at building a world-class interdisciplinary research and educational center for data science. SDS has over 90 faculty members, many of whom have experience at top-tier universities and significant international impacts in their fields. The school is now inviting qualified candidates to fill multiple teaching-stream faculty positions. The primary duties are to teach courses for multiple programs offered by the school.Applicants should hold or expect to obtain a Ph.D. degree in one or more of the following areas: Computer Systems (including architecture, HPC, security, software engineering, database etc.), Machine Learning, AI for Science and Engineering, Theoretical Computer Science, Operations Research, Data Science, Statistics, Biostatistics, Stochastic Modelling, Quantum Information Theory, Management Science, and other closely related areas.Junior applicants must demonstrate a clear and…

The School of Data Science (SDS) at The Chinese University of Hong Kong, Shenzhen (CUHK-SZ) aims at building a world-class interdisciplinary research and educational center for data science. SDS has over 90 faculty members, many of whom have experience at top-tier universities and significant international impacts in their fields. The school is now inviting extraordinarily qualified candidates to fill multiple tenured or tenure-track positions at all academic ranks.We seek applicants with outstanding methodological foundations in one or more of the following areas: Computer Systems (including architecture, HPC, security, software engineering, database etc.), Machine Learning, AI for Science and Engineering, Theoretical Computer Science, Operations Research, Data Science, Statistics, Biostatistics, Stochastic Modelling, Quantum Information Theory, Management Science, and other closely related areas.We especially encourage individuals whose interests and backgrounds are at the…

Yaoming Zhen is an Assistant Professor in the School of Data Science at The Chinese University of Hong Kong, Shenzhen. Before joining CUHK-Shenzhen, he served as a Postdoctoral Fellow in the Department of Statistical Sciences at the University of Toronto, where he was mentored by Elena Tuzhilina, Piotr Zwiernik, and Qiang Sun. Yaoming was a Hong Kong PhD Fellowship Scheme (HKPFS) awardee and earned his Ph.D. in Data Science from the City University of Hong Kong in 2023, under the supervision of Junhui Wang. He obtained a B.S. in Mathematics from the Yat-sen School and the School of Mathematics at Sun Yat-sen University in 2019. Additionally, he visited the University of California, Berkeley, from the fall of 2022 to the spring of 2023 and also in the spring of 2018, serving as a visiting student researcher and participating in the Berkeley International Study Program, respectively. Dr. Zhen’s research primarily focuses on tensor-based statistical machine learning, which further links…