Speaker: Prof. Yang Liu, UC Santa Cruz
Time: 11:00-12:00 , Dec.02
Location: SIST2 302A
Host: Prof. Yong Zhou
Abstract:
Learning from weak supervisions is a prevalent challenge in machine learning: in supervised learning, the training labels are often solicited from human annotators, which encode human-level mistakes; in semi-supervised learning, the artificially supervised pseudo labels are immediately imperfect; in reinforcement learning, the collected rewards can be misleading, due to faulty sensors. The list goes on. In this talk, I will first introduce recent efforts on designing robust loss functions that can correct the misled training objectives by noisy labels. I will explain both the theoretical and empirical advantages of these approaches. Then I will present a set of new arising challenges. Among them, I’ll show the “Matthew effect” of most of the existing solutions. This observation cautions the use of these tools and provides a new evaluation criterion for future developments.
Bio:
Dr. Yang Liu is currently an Assistant Professor of Computer Science and Engineering at UC Santa Cruz. He was previously a postdoctoral fellow at Harvard University. He obtained his PhD degree from the Department of EECS, University of Michigan, Ann Arbor in 2015. He is interested in crowdsourcing and algorithmic fairness, both in the context of machine learning. His works have seen applications in high-profile projects, such as the Hybrid Forecasting Competition organized by IARPA, and Systematizing Confidence in Open Research and Evidence (SCORE) organized by DARPA. His works have also been covered by WIRED and WSJ. His works have won three best paper awards.
沪公网安备 31011502006855号
