Multi-task Additive Models for Robust Estimation and Automatic Structure Discovery

讲座时间 Datetime: 2022年11月30日，星期三，15：00-16：00

地点 Venue: 腾讯会议127-810-205

主持人 Host：张海樟 教授

报告人 Speaker: 陈洪 教授

单位 Affiliation: 华中农业大学理学院

报告摘要 Abstract:

Additive models have attracted much attention for high-dimensional regression estimation and variable selection. However, the existing models are usually limited to the single-task learning framework under the MSE criterion, where the utilization of variable structure depends heavily on a priori knowledge among variables. For high-dimensional observations in real environment, the learning performance of previous methods may be degraded seriously due to the complex non-Gaussian noise and the insufficiency of a prior knowledge on variable structure. To tackle this problem, we propose a new class of additive models, called Multi-task Additive Models (MAM), by integrating the mode-induced metric, the structure-based regularizer, and additive hypothesis spaces into a bilevel optimization framework. Our approach does not require priori knowledge of variable structure and suits for high-dimensional data with complex noise. Some theoretical analysis and empirical evaluations are established for the proposed MAM.

报告人简介：
陈洪，华中农业大学教授、博士生导师。研究方向为机器学习、统计学习理论。主持国家自科基金面上项目等5项国家级课题，在Appl. Comput.Harmon. Anal、J. Approx.Theory、IEEE TPAMI/TNNLS/TCYB、Neural Computation、Neural Networks等数学与信息交叉领域期刊发表论文50余篇，在人工智能顶会NeurIPS、ICML、ICLR、AAAI发表论文13篇。华中农业大学硕彦计划拔尖人才，曾任匹兹堡大学兼职研究员、德州大学阿灵顿分校博士后研究员。