Faculty Profiles
Jun-Kun Wang
Assistant Professor, Electrical and Computer Engineering
Theory and Applications of Optimization, Sampling, Online Learning, Game Theory, Trustworthy Machine Learning
Wang's research aims to make algorithms faster, build robust theoretical foundations with simple analysis, and overcome issues such as model mis-specification or distribution shifts encountered during the deployment of machine learning methods in real-world contexts. His primary focus is acceleration in optimization, sampling, and machine learning with strong theoretical guarantees, which encompasses designing momentum methods in both convex and non-convex optimization, accelerating algorithms through innovative parameter value schemes, and leveraging insights from one domain to enhance algorithms in another, and vice versa. He also focuses on optimization for trustworthy machine learning, which includes the development of computationally efficient methods in this field.
Capsule Bio:
Jun-Kun Wang joined UC San Diego in July 2023. He has a joint appointment with the Department of Electrical and Computer Engineering and the Halicioğlu Data Science Institute. Prior to that, he was a postdoc at Yale University. He received his Ph.D. in CS from Georgia Tech and holds an M.S. in Communication Engineering and a B.S. in Electrical Engineering from National Taiwan University.
He has been working on optimization, sampling, and machine learning. He likes discovering connections between different research areas, e.g., optimization and no-regret learning, optimization and sampling, optimization and tackling distribution shifts. Many of his research works are published in the proceedings of top-tier machine learning conferences and prestigious optimization journals, including COLT, ICML, ICLR, NeurIPS, and Mathematical Programming.
Selected Publications:
