报告人:王世雄 博士,帝国理工学院
报告时间:2024年9月19日,下午4:00-6:00
报告地点:线上腾讯会议 987-655-349
报告题目:Learning Against Distributional Uncertainty: On the Trade-off Between Robustness and Specificity
报告摘要:
Trustworthy machine learning aims at combating distributional uncertainties in training data distributions compared to population distributions. Typical treatment frameworks include the Bayesian approach, (min-max) distributionally robust optimization (DRO), and regularization.
However, three issues have to be raised: 1) the prior distribution in the Bayesian method and the regularizer in the regularization method are difficult to specify; 2) the DRO method tends to be overly conservative; 3) all the three methods are biased estimators of the true optimal cost. We study a new framework that unifies the three approaches and addresses the three challenges above. The asymptotic properties (e.g., consistencies and asymptotic normalities), non-asymptotic properties (e.g., generalization bounds and unbiasedness), and solution methods of the proposed model are studied. The new model reveals the trade-off between the robustness to the unseen data and the specificity to the training data. Experiments on various real-world tasks validate the superiority of the proposed learning framework. In addition, we discuss the applications in wireless communications.
个人简介:
王世雄博士于2016年7月获得西北工业大学电子信息学院探测制导与控制技术专业工学学士学位(优秀学位论文),同年9月免试录取为西北工业大学电子信息学院系统与控制工程系硕士,并于2018年5月提前一年毕业并获得西北工业大学电子信息学院系统与控制工程系工学硕士学位(优秀学位论文)。他于2022年7月获得新加坡国立大学工业系统工程与管理系哲学博士学位。 在2022年3月至2023年3月期间,他是新加坡国立大学数据科学研究院博士后研究员。自2023年5月以来,他在帝国理工学院智能传输与处理实验室担任博士后研究员。他的主要研究方向包含统计信号处理与统计机器学习。更多信息详见个人主页:https://wangsx-cn.github.io/。