讲座题目:Bayesian Quantile Regression (BQR): the State of the Art and Future Research
主讲人:虞克明
讲座时间:2024年3月27日(周三) 14:00-16:00
讲座地点:综合楼644会议室
主讲人简介:
虞克明,英国伦敦布鲁内尔大学统计学与数据科学讲习教授(Chair Professor)、 数学学科研究影响中心主任;英国皇家统计学会会士、英国社科基金 (ESRC) 评审专家成员、英国自科基金 (EPSRC)评审专家成员 、欧洲科学基金(ESF) 评审专家成员。目前是《Journal of the American Statistical Association, A&CS》副主编,也担任过《Journal of the Royal Statistical Society-A》等多家国际SCI、SSCI期刊的副主编。目前他主要从事回归分析、 非参数统计、 机器学习、 贝叶斯推断、大数据及非常小的数据分析等方面的理论和方法研究,是贝叶斯分位数回归方法的开拓者,先后在《Journal of American Statistical Association》、《Journal of the Royal Statistical Society: Series B》、《Journal of Econometrics》、《Journal of Business & Economic Statistics》、《Bernoulli》等统计学顶级刊物上发表论文150多篇。
讲座摘要:
As certain statistical theories within the frequentist framework encounter challenges in the AI era, Bayesian methods like Bayesian Neural Networks (BNNs) and Bayesian Deep Learning (BDL) are gaining popularity and are expected to continue doing so. Concurrently, Bayesian quantile regression (BQR), including Bayesian Tobit quantile regression, which we have championed, are gradually gaining recognition worldwide. This presentation aims to provide a review of the state of the art and future research directions, following a brief overview of quantile regression (QR).