腾讯会议 ：611-187-563

主讲人姓名 ：陈洪 华中农业大学教授

主讲人简介 ：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，在人工智能顶会NeurIPS、ICML、ICLR和期刊IEEE TPAMI/TNNLS/TCYB、Neural Computation、Neural Networks等期刊发表论文40余篇。

报告题目 ：Multi-task Additive Models for Robust Estimation and Automatic Structure Discovery

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 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. A smooth iterative optimization algorithm with convergence guarantees is provided to implement MAM efficiently. Experiments demonstrate the competitive performance of our approach for robust estimation and automatic structure discovery.