Skip to content
Title: Constrained optimization: application, algorithm and complexity
Speaker: Dr. Yue Xie, Research Assistant Professor, IDS & Department of Mathematics, HKU
Date: Jun 7, 2023
Time: 10:30am – 11:30am

Mode: Hybrid. Seats for on-site participants are limited. A confirmation email will be sent to participants who have successfully registered.

Abstract

In this talk, the speaker will discuss constrained optimization. The speaker will focus on two important subclasses: bound-constrained nonconvex optimization and linear programming. Typical applications of them include nonnegative matrix factorization and optimal transport (OT) problems, which are popular topics in both mathematics and data science. To resolve the former subclass, the speaker will propose a projected Newton-CG algorithm. This algorithm is designed to possess both practicality and worst-case complexity guarantees matching the best known in literature. For the linear programming formulation of OT, the speaker will discuss random block coordinate descent (RBCD) methods. A direct advantage of these methods is to save memory. In addition, the speaker and his team’s preliminary numerical experiments show that it competes well with the classical Sinkhorn’s algorithm.

Speaker

Dr. Yue Xie
Research Assistant Professor @ HKU IDS & Dept of Mathematics
Dr. Yue Xie is a Research Assistant Professor in Musketeers Foundation Institute of Data Science (HKU-IDS) and Department of Mathematics at the University of Hong Kong. He was a postdoc at UW Madison working in the nonconvex optimization group led by Professor Stephen J. Wright. He received his PhD degree in Pennsylvania State University and Bachelor degree from Tsinghua University. Dr. Yue Xie has been focusing on algorithm design and analysis to address nonconvex and stochastic optimization problems with all types of applications including machine learning and data science. He has published/served as the referee of top-tier journals including Mathematical Programming, SIAM Journal on Optimization, and IEEE Transactions on Automatic Control, etc. He has delivered numerous presentations at major international conferences such as International Conference on Continuous Optimization (ICCOPT), International Symposium on Mathematical Programming (ISMP), SIAM Conference on Optimization and International Conference on Machine Learning (ICML).
More details about him can be found at: https://yue-xie.github.io.

For information, please contact:
Email: datascience@hku.hk