Assistant Professor, Computer Science | Member of the Graduate Faculty
My research is centered around sequential decision-making in feedback loops i.e. the multi-armed bandit problem) and online machine, not human) learning. I also had some fun in the past with machine learning applied to psychology. I was previously a postdoc with Francesco Orabona at Boston University. Before then, I spent 9 years at UW-Madison for a PhD degree with Xiaojin Jerry) Zhu and a postdoc position at Wisconsin Institute for Discovery with Robert Nowak, Rebecca Willett, and Stephen Wright.
The National Science Foundation has awarded a grant to Computer Science researcher Kwang-Sung Jun for a project focused on improving Monte Carlo tree search (MCTS), a versatile method for sequential decision-making. The project aims to bridge the gap between theory and practice in MCTS by developing new algorithms with strong mathematical guarantees, establishing optimal performance rates, and evaluating them in real-world applications.
Key aspects of the grant:
- Improving existing MCTS algorithms with strong theoretical guarantees
- Establishing optimal performance rates for MCTS algorithms
- Evaluating developed algorithms in material science tasks with undergraduate teams
- Developing a course module and open-source software for MCTS research and education.