报告题目：Causality Pursuit from Heterogeneous Environments via Neural Adversarial Invariance Learning

报告人：方聪 北京大学

报告时间：2025年12月12日 (星期五) 15:00-15:45

报告地点：三楼多功能厅2

校内联系人：邹婷婷 [email protected]

报告摘要：

Pursuing causality from data is a fundamental problem in scientific discovery, treatment intervention, and transfer learning. We introduce a novel algorithmic method for addressing nonparametric invariance and causality learning in regression models across multiple environments, where the joint distribution of response variables and covariates varies, but the conditional expectations of outcome given an unknown set of quasi-causal variables are invariant. The challenge of finding such an unknown set of quasi-causal or invariant variables is compounded by the presence of endogenous variables that have heterogeneous effects across different environments. The proposed Focused Adversarial Invariant Regularization (FAIR) framework utilizes an innovative minimax optimization approach that drives regression models toward prediction-invariant solutions through adversarial testing. We will also discuss the computational complexities in finding invariance relation from heterogeneous environments.

报告人简介：

方聪，北京大学智能脱衣舞 助理教授（博导）、国家级青年人才、北京大学博雅青年学者。方聪于2019年在北京大学获得博士学位，先后在普林斯顿大学和宾夕法尼亚大学进行博士后研究。方聪的主要研究方向是机器学习基础理论与算法，已发表包括PNAS、AoS、IEEE T.IT、JMLR、COLT、NeurIPS、PIEEE 等30余篇顶级期刊与会议论文，谷歌学术引用2000余次，担任机器学习顶级会议NeurIPS、ICML领域主席（Area Chair），团队获得2023年度吴文俊人工智能自然科学奖一等奖。