Centre-augmented L2-type regularization for subgroup learning
报告人： 林华珍（西南财经大学）
时间：2022-05-27 15:00-16:30
地点：腾讯会议（497-510-590）
Abstract:
The existing methods for subgroup analysis can be roughly divided into two categories: finite mixture models (FMM) and regularization methods with an L1 -type penalty. In this paper, by introducing the group centres and L2 -type penalty in the loss function, we propose a novel centre-augmented regularization (CAR) method; this method can be regarded as a unification of the regularization method and FMM and hence exhibits higher efficiency and robustness and simpler computations than the existing methods. Particularly, its computational complexity is reduced from the $O(n^2)$ of the conventional pairwise-penalty method to only $O(nK)$, where n is the sample size and K is the number of subgroups. The asymptotic normality of CAR is established, and the convergence of the algorithm is proven. CAR is applied to a dataset from a multicenter clinical trial: Buprenorphine in the Treatment of Opiate Dependence; a larger $R^2$ is produced and three additional significant variables are identified compared to those of the existing methods.
About the Speaker:
林华珍，西南财经大学教授，统计研究中心主任，国际数理统计学会IMS-fellow， 教育部长江学者特聘教授，国家杰出青年科学基金获得者，国家百千万人才工程获得者，享受国务院政府特殊津贴专家。林华珍教授主要的研究方向为非参数方法、转换模型、生存数据分析、函数型数据分析、潜变量分析、时空数据分析。研究成果发表在包括国际统计学四大顶级期刊AoS、JASA、JRSSB、Biometrika 和计量经济学顶级期刊JOE 及JBES 上。她先后多次主持国家基金项目，包括国家杰出青年基金及自科重点项目。林华珍教授是国际IMS-China、IBS-CHINA 及ICSA-China 委员，中国现场统计研究会数据科学与人工智能分会理事长，第九届全国工业统计学教学研究会副会长，中国现场统计研究会多个分会的副理事长。她先后是国际统计学权威期刊《Biometrics》、《Scandinavian Journal of Statistics》、《Journal of Business & Economic Statistics》、《Canadian Journal of Statistics》、 《Statistics and Its Interface》、《Statistical Theory and Related Fields》的Associate Editor， 国内权威或核心学术期刊《数学学报》(英文)、《应用概率统计》、《系统科学与数学》、《数理统计与管理》编委会编委。
Tencent Meeting: https://meeting.tencent.com/dm/byngCKh37z73
Meeting ID: 497-510-590
Your participation is warmly welcomed!
欢迎扫码关注北大统计科学中心公众号，了解更多讲座信息!
