Kenji Fukumizu
A co-authored paper received Student Paper Award (Honorable Mention) in NIPS 2009!Bharath Sriperumbudur et al.: Kernel Choice and Classifiability for RKHS Embeddings of Probability Distributions.
My research Interest:
I am interested in thoery and practice of learning with complex and structured data, and working from the viewpoints of statistics, mathematics and machine learning. More specific research projects include the following topics;
- Kernel method (data analysis with positive definite kernels): Nonparametric data analysis with positive definite kernels and reproducing kernel Hilbert spaces. Expressing probabilistic knowledge using embedding of data in reproducing kernel Hilbert spaces, and its applications to extracting dependence, conditional dependence structure among variables. Inference of causal networks with these methods.
- Geometry of algorithms on graphs: Analysis of algorithms on graphs, such as belief propagation, with graph geometry, graph polynomial and so on.
- Singular statistical models: Statistical inference with parametric models with singularities. Nonstandard asymptotic behavior of the estimator around sigularities.
Welcome! I welcome students and collaborators interested in the above topics. Contact me by email.
Publications
Students
- Yusuke Watanabe (D2)
- Md Ashad Alam (M1)
Alumni
- Yuichi Shiraishi (Riken)
- Tomoko Ikeda-Fukazawa (Meiji Unversity)
- Marco Cuturi (Princeton University)