Yushun Zhang
About meI'm a Ph.D student in School of Data Science at The Chinese University of Hong Kong, Shenzhen, China. I'm very proud to be advised by Prof. Zhi-Quan (Tom) Luo. I’m also very fortunate to work closely with Prof. Ruoyu Sun. Previously, I did my undergraduate study in the Department of Mathematics at Southern University of Science and Technology (SUSTech). My research focuses on optimization, deep learning, and especially, large language models. I aim to work on important and practical problems with optimization flavor. Research that I lead or co-leadAdam-mini: Use Fewer Learning Rates To Gain More Why Transformers Need Adam: A Hessian Perspective Adam Can Converge Without Any Modification on Update Rules Does Adam Converge and When? When Expressivity Meets Trainability: Fewer than n Neurons Can Work Research that I proudly participate inReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models Provable Adaptivity of Adam under Non-Uniform Smoothness HyperDQN: A Randomized Exploration Method for Deep Reinforcement Learning Fast QLB algorithm and hypothesis tests in logistic model for ophthalmologic bilateral correlated data Invited TalksOct 2024: I gave a talk at U of Minnesota, hosted by Prof. Mingyi Hong. Thanks Prof. Hong for the invitation!
Oct 2024: I gave a talk at INFORMS Anneal Meeting, Seattle, hosted by Jianhao Ma. Thanks Jianhao for the invitation!
Sep 2023: I gave a talk at Tsinghua University, hosted by Prof. Jian Li. Thanks Prof. Li for the invitation!
Jan 2023: I gave a talk at Google Brain, hosted by Dr. Diederik P. Kingma. Thanks Dr. Kingma for the invitation!
Awards (By time)Duan Yongping Outstanding Resesearch Award (1st place), 2023 Teaching Assistant Award, School of Data Science, 2023 Best Paper Presentation Award (1st place), 2nd Doctoral and Postdoctoral Daoyuan Academic Forum, 2022
Best Paper Presentation Award (1st place), 3rd Tsinghua-Berkeley workshop on Learning Theory, 2021
Magna cum laude of SUSTech, 2019 Outstanding graduation thesis, SUSTech, 2019 Scholarship Award for Excellence, Mathematics department, SUSTech (Top 10 students) , 2018 ServicesReviewerI serve as a reviewer for machine learning conferences including NeurIPS, ICLR, ICML, COLT, AISTATS, as well as journals including JMLR and TMLR. Social ActivitiesI hosted a session named “Optimization Issues in Recent AI Models” at INFORMS Anneal Meeting, Oct, 2024. Teaching Assistant (by time)
ExperiencesI spent a great time as an exchange undergraduate student at Mathematics department, UC San Diego, 2019 Spring. I spent the best three years at the Shenzhen Foreign Language School, branch, 2009 - 2012. |