报告题目: Self-Supervised Metric Learning in Multi-View Data: A Downstream Task Perspective
主 讲 人：SHULEI WANG
报告时间：2022年4月20日上午9:30-10:30
报告地点：腾讯会议 会议 ID：282-942-037
点击链接入会：https://meeting.tencent.com/dm/caBPWvrOkJoL
报告摘要:
Self-supervised metric learning has been a successful approach for learning a distance from an unlabeled dataset. The resulting distance is broadly useful for improving various distance-based downstream tasks, even when no information from downstream tasks is utilized in the metric learning stage. To gain insights into this approach, we develop a statistical framework to theoretically study how self-supervised metric learning can benefit downstream tasks in the context of multi-view data. Under this framework, we show that the target distance of metric learning satisfies several desired properties for the downstream tasks. On the other hand, our investigation suggests the target distance can be further improved by moderating each direction’s weights. In addition, our analysis precisely characterizes the improvement by self-supervised metric learning on four commonly used downstream tasks: sample identification, two-sample testing, k-means clustering, and k-nearest neighbor classification. When the distance is estimated from an unlabeled dataset, we establish the upper bound on distance estimation’s accuracy and the number of samples sufficient for downstream task improvement.
主讲人介绍：
SHULEI WANG is an Assistant Professor in the Department of Statistics at the University of Illinois at Urbana-Champaign. Previously, he was a postdoc researcher at the University of Pennsylvania. He received Ph.D. in Statistics from the University of Wisconsin-Madison under supervision by Ming Yuan. His research interests lie in the intersection of statistical methodology and thoery (nonparametric and high-dimensional statistics) and its biomedical applications (microbiome and imaging). He has published his work on TOP statistics journals such as Journal of American Statistical Association, Biometrika.
邀请人：何勇
欢迎各位老师同学积极参加！
