YANG, Junchi
POSITION/TITLE
Research Scientist
Assistant Professor of CUHK-Shenzhen
Education Background
Ph.D. Computer Science, ETH Zurich, 2023
M.S. Industrial Engineering, University of Illinois Urbana-Champaign, 2020
B.S., B.A. Applied Mathematics & Economics, UCLA, 2017
Research Field
Continuous Optimization and Its Applications in Machine Learning and Energy Systems
Personal Website
https://junchi-michael-yang.github.io/
yangjunchi@cuhk.edu.cn
Biography
Dr. Junchi Yang is an Assistant Professor at the School of Data Science, The Chinese University of Hong Kong, Shenzhen (CUHK-SZ). Before joining CUHK-SZ, he was a postdoctoral researcher at Argonne National Laboratory. Dr. Yang holds a Ph.D. in Computer Science from ETH Zurich, a Master’s degree in Industrial Engineering from the University of Illinois Urbana-Champaign (UIUC), and a Bachelor’s degree in Applied Mathematics and Economics from the University of California, Los Angeles (UCLA).
Dr. Yang's research is dedicated to developing advanced continuous optimization algorithms to address complex and strategic decision-making challenges, with a particular focus on applications in machine learning and the energy systems. His work has been published in leading academic venues such as NeurIPS and ICLR.
Academic Publications
(* indicates equal contribution)
1. Florian Hübler, Junchi Yang, Xiang Li, and Niao He. Parameter-Agnostic Optimization under Relaxed Smoothness. International Conference on Artificial Intelligence and Statistics (AISTATS 2024).
2. Junchi Yang*, Xiang Li*, Ilyas Fatkhulin, and Niao He. Two Sides of One Coin: the Limits of Untuned SGD and the Power of Adaptive Methods. Conference on Neural Information Processing Systems (NeurIPS 2023).
3. Liang Zhang*, Junchi Yang*, Amin Karbasi, Niao He. Optimal Guarantees for Algorithmic Reproducibility and Gradient Complexity in Convex Optimization. Conference on Neural Information Processing Systems (NeurIPS 2023). Spotlight.
4. Xiang Li, Junchi Yang, and Niao He. TiAda: A Time-Scale Adaptive Algorithm for Nonconvex Minimax Optimization. International Conference on Learning Representations (ICLR 2023).
5. Junchi Yang*, Xiang Li*, and Niao He. Nest Your Adaptive Algorithm for Parameter-Agnostic Nonconvex Minimax Optimization. Conference on Neural Information Processing Systems (NeurIPS 2022).
6. Junchi Yang, Antonio Orvieto, Aurelien Lucchi, and Niao He. Faster Single-Loop Algorithms for Minimax Optimization without Strong Concavity. International Conference on Artificial Intelligence and Statistics (AISTATS 2022).
7. Siqi Zhang*, Junchi Yang*, Cristóbal Guzmán, Negar Kiyavash, and Niao He. The Complexity of Nonconvex-Strongly-Concave Minimax Optimization. Conference on Uncertainty in Artificial Intelligence (UAI 2021).
8. Junchi Yang, Siqi Zhang, Negar Kiyavash, and Niao He. A Catalyst Framework for Minimax Optimization. Conference on Neural Information Processing Systems (NeurIPS 2020).
9. Junchi Yang, Negar Kiyavash, and Niao He. Global Convergence and Variance-Reduced Optimization for a Class of Nonconvex-Nonconcave Mini-max Problems. Conference on Neural Information Processing Systems (NeurIPS 2020).
