报告题目：Co-Sparse Estimation of Reduced-Rank Regression via L0 Norm
报告人：董枘朋
邀请人：黄磊
讲座时间：2026年5月18日（星期一）上午10:00
讲座地点：犀浦校区三号教学楼X30423
报告摘要：Sparse reduced-rank regression is a widespread tool to reveal the association between multiple responses and predictors, and it has been widely applied to many data-driven applications. Although much of the literature has studied related theoretical properties and numerical algorithms, due to high nonconvexity, the computation burden for large-scale data sets remains a great challenge in practice. Also, the gap between the statistical consistency and the algorithmic convergence needs more research. To address these two issues, we formulate a sparse reduced-rank regression as a set of parallel co-sparse unit-rank estimation problems and propose a new algorithm to estimate these subproblems in parallel. Under mild conditions, the iteration complexity of the proposed algorithm is polynomial with high-dimensional responses and predictors. We show a statistical consistency for the numerical solution, thereby bridging the gap between statistical consistency and numerical computation from nonconvex optimization. Moreover, the main calculation of the algorithm is restricted to a small active set, so it exhibits fast computation even in high dimensions. Extensive numerical studies and an application in genetics demonstrate the effectiveness and scalability of our approach..
主讲人简介：董枘朋，西南交通大学数学学院本科毕业，中国科学技术大学管理学院博士毕业，现任合肥工业大学经济学院教授，黄山学者优秀青年。主要从事高维统计、数据科学与市场营销等领域的交叉研究工作。先后主持国家自然科学基金青年项目、中国博士后科学基金面上项目、中国科学技术大学青年创新基金等多项课题，在INFORMS Journal on Computing、Statistics and Computing、Journal of Machine Learning Research、Statistics & Probability Letters、Computational Statistics & Data Analysis等学术期刊发表论文10余篇。曾荣获中国科学技术大学墨子杰出青年特资津贴资助。担任INFORMS Journal on Computing、Journal of Business & Economic Statistics、Computational Statistics & Data Analysis、Statistics and Computing等期刊匿名审稿人。