- Reinforcement learning: design effective algorithms by exploiting the intrinsic structures in the uncertain dynamics for automatic decision making.
- Learning to design algorithms: improve the algorithms, e.g., sampling, searching and planning, by leveraging empirical experiences.
- Structured input and output: build effective models for capturing the structures information in input and output, e.g., binaries, sequences, programs, trees, and graphs.
My research interests lie on designing principled machine learning methods. Currently, I mainly focus on three major themes: