报告人：陈洪（华中农业大学）

报告题目：Bilevel Additive Models

报告摘要：As an important paradigm in statistical machine learning, additive models often exhibit excellent capabilities on function approximation and variable selection. This report will explore the construction and algorithmic implementation of bilevel additive models, with focus on three issues including: (1) How to realize the data-driven structure discovery of variable groups? (2) How to automatically design the appropriate loss function? (3) How to mitigate the impact of noisy features on manifold learning? In theory, the report analyzes the upper bounds of generalization error and the consistency of variable selection. In applications, the effectiveness of bilevel additive models has been validated through data experiments.

报告时间：2024年10月27日（星期日）15:30-17:00

报告地点：东三十二楼102室

邀请人：刘海霞

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，在人工智能顶会NeurIPS、ICML、ICLR等发表论文20余篇, 在ACHA、JAT、IEEETPAMI/TIP/TNNLS/TCYB等期刊发表论文40余篇，在Nature Genetics等发表智慧农业交叉应用论文。主持国家级项目6项，其中国家自然科学基金面上项目3项。