My principal research interests lie in developing effective statistical models and efficient algorithms for learning from a massive volume of complex, structured, uncertain and high-dimensional data.
Articularly, I am focusing on core machine learning methodology for large-scale structured data, including,
Large-scale nonparametric machine learning: develop efficient algorithms for machine learning methods, especially nonparametric methods, to handle hundreds of millions of data.
Learning with complex distributions, structures, and dynamics:
Reinforcement learning: design effective algorithms for exploiting the recursive structure in the dynamics.
Structured input and output: build effective models for capturing the structures information in input and output, e.g., binaries, sequences, trees, and graphs.