Songbai Yan PhD Student Department of Computer Science and Engineering University of California, San Diego Office: EBU3B 4142 Email: lastnamefirstname dot eng dot ucsd dot edu

About I defended my thesis and joined Google Waterloo as a software engineer. I did my PhD with Prof. Kamalika Chaudhuri and Prof. Tara Javidi. My research focused on algorithms and theory for learning with human in the loop. In particular, I studied new annotation schemes for active learning that improve the quality of human annotations and thus allow for annotation-effective learning. I also worked on active learning algorithms with theoretical guarantees that properly handle annotation mistakes and side information. Prior to that, I received my bachelor's degree in 2014 from Department of Computer Science and Technology at Peking University, where I worked with Prof. Liwei Wang on various topics in learning theory.

Publications Varun Chandrasekaran, Kamalika Chaudhuri, Irene Giacomelli, Somesh Jha and Songbai Yan Exploring Connections Between Active Learning and Model Extraction USENIX Security, 2020 Songbai Yan, Kamalika Chaudhuri and Tara Javidi The Label Complexity of Active Learning from Observational Data Neural Information Processing Systems (NeurIPS), 2019 Songbai Yan, Kamalika Chaudhuri and Tara Javidi Active Learning with Logged Data International Conference on Machine Learning (ICML), 2018 Songbai Yan, Chicheng Zhang Revisiting Perceptron: Efficient and Label-Optimal Learning of Halfspaces Neural Information Processing Systems (NIPS), 2017 Songbai Yan, Kamalika Chaudhuri and Tara Javidi Active Learning from Imperfect Labelers Neural Information Processing Systems (NIPS), 2016 Songbai Yan, Kamalika Chaudhuri and Tara Javidi Active Learning from Noisy and Abstention Feedback Allerton Conference on Communication, Control and Computing, 2015 Kai Fan, Hongyi Zhang, Songbai Yan, Liwei Wang, Wensheng Zhang, Jufu Feng Learning a Generative Classifier with Label Proportions Neurocomputing, 2014

Reports Songbai Yan Passive and Active Ranking from Pairwise Comparisons Research Exam, UCSD, 2016