报告人简介
邹长亮，南开大学统计与数据科学学院教授、统计研究院院长。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：高维数据统计推断、变点和异常点检测、预测性推断等，在统计学和机器学习领域的权威杂志/会议Ann.Stat.、Biometrika、J.Am.Stat.Asso.、J.Mach.Learn.Res.、Math.Program.、ICML/NIPS/AAAI等上发表论文数十篇篇，入选爱思唯尔“中国高被引学者”。主持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。
内容简介
In multiple changepoint analysis, assessing the uncertainty of detected changepoints is crucial for enhancing detection reliability—a topic that has garnered significant attention. Despite advancements through selective p-values, current methodologies often rely on stringent assumptions tied to specific models and algorithms, potentially compromising the accuracy of post-detection statistical inference. We introduce TUNE (Thresholding Universally and Nullifying change Effect), a novel algorithm-agnostic approach that uniformly controls error probabilities across detected changepoints. TUNE sets a universal threshold for multiple test statistics, applicable across a wide range of algorithms, and directly controls the family-wise error rate without the need for selective p-values. Through extensive theoretical and numerical analyses, TUNE demonstrates versatility, robustness, and competitively power, offering a viable and reliable alternative for model-agnostic post-detection inference.
