Jun-Kun Wang

Jun-Kun Wang is an Assistant Professor in the Department of Electrical and Computer Engineering at the University of California, San Diego. His research focuses on optimization, sampling, and machine learning, with an emphasis on developing efficient algorithms and addressing challenges such as model mis-specification and distribution shifts. Wang has a joint appointment with the Halicioğlu Data Science Institute. Prior to joining UC San Diego in July 2023, 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. His work has been published in top-tier machine learning conferences and optimization journals.

Jun-Kun Wang is an Assistant Professor at the University of California San Diego, specializing in optimization and machine learning. His research focuses on developing efficient algorithms for convex and non-convex optimization problems, with applications in machine learning and statistical inference. Wang's work explores topics such as acceleration techniques, no-regret dynamics, and stochastic optimization methods. He has contributed to the understanding of convex-concave games, Frank-Wolfe algorithms, and the role of momentum in optimization. His research also addresses challenges in online learning, robust estimation, and test-time adaptation. Wang's publications highlight the interplay between optimization theory and practical machine learning applications.