报告名称：Multi-task Additive Models

主办单位：英国立博官网中文版

报告专家：陈洪

专家所在单位：华中农业大学

报告时间：2020年8月24日9:00-11:30

报告地点：腾讯会议779 403 665

专家简介：陈洪，华中农业大学教授，博士生导师。研究方向为机器学习、学习理论、逼近论。2009.6博士毕业于湖北大学基础数学专业，湖北省优秀博士论文获得者。2016.3-2017.8在University of Texas at Arlington从事博士后研究，多次受邀请赴澳门大学、香港城市大学等进行合作研究。主持国家自然科学基金面上项目、青年基金等多项科研课题，在Appl. Comput. Harmon. Anal., J. Approx. Theory, IEEE TPAMI, IEEE TNNLS, IEEE T. Cybernetics, Neural Networks, Neural Computation, Bioinformatics等知名期刊发表SCI论文20余篇，在机器学习顶级会议NIPS发表论文多篇。

报告摘要：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 mean squared error (MSE) criterion, where the utilization of variable structure depends heavily on priori knowledge among variables. For high-dimensional observations in real environment, e.g., Coronal Mass Ejections (CMEs) data, the learning performance of previous methods may be degraded seriously due to the complex non-Gaussian noise and the insufficiency of 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 any priori knowledge of variable structure and suits for high-dimensional data with complex noise, e.g., skewed noise, heavy-tailed noise, and outliers. A smooth iterative optimization algorithm with convergence guarantees is provided to implement MAM efficiently. Experiments on simulations and the CMEs analysis demonstrate the competitive performance of our approach for robust estimation and automatic structure discovery.

邀请人：邹斌