Qingyun Wu

"Learning by Exploration in an Unknown and Changing Environment"

( MPI-SWS talk in Kooperation mit dem Fachbereich Informatik)

Learning is a predominant theme for any intelligent system, humans or machines. Moving beyond the classical paradigm oflearning from past experience, e.g., supervised learning from given labels, a learner needs to actively collectexploratory feedback to learn the unknowns. Considerable challenges arise in such a setting, including samplecomplexity, costly and even outdated feedback.In this talk, I will introduce our themed efforts on developing solutions to efficiently explore the unknowns anddynamically adjust to the changes through exploratory feedback. Specifically, I will first present our studies inleveraging special problem structures for efficient exploration. Then I will present our work on empowering the learnerto detect and adjust to potential changes in the environment adaptively. Besides, I will also highlight the impact ourresearch has generated in top-valued industry applications, including online learning to rank and interactiverecommendation.

Bio: Qingyun Wu is a Ph.D. candidate in the Department of Computer Science, University of Virginia. Her research focuses oninteractive online learning, including bandit algorithms, reinforcement learning, and their applications in real-worldproblems. Her research has appeared in multiple top-tier venues, including SIGIR, WWW, KDD, and NeurIPS; and heralgorithms have been evaluated in several commercial systems in industry (including Yahoo news recommendation andSnapchat lens recommendation). Qingyun received multiple prestigious awards from the University of Virginia for herexcellence in research, including the Virginia Engineering Foundation Fellowship and the Graduate Student Award forOutstanding Research. Her recent work on online learning to rank won the Best Paper Award of SIGIR'2019. She was alsoselected as one of the Rising Stars in EECS 2019.

Termin als Datei downloaden und in den Kalender importieren.