Hilbert space embedding of probability distributions
Add to your list(s)
Download to your calendar using vCal
If you have a question about this talk, please contact Shakir Mohamed.
The seminar will focus on representing probability measures via mean elements in characteristic reproducing Hilbert spaces.
In particular I plan to talk about:
- RKHS ’s and characteristic kernels in general
- homogeneity and independence testing using RKH Ss
- density estimation via kernel moment matching
Recommended reading:
- Gretton et al: A Kernel Method for the Two-Sample Problem, NIPS ‘08, pdf
- recently updated Song et al: Tailoring Density Estimation via Reproducing Kernel Moment Matching www
- Gretton et al: Measuring Statistical Dependence with Hilbert Schmidt norms, ALT ’05, pdf
Further reading/material:
- Gretton et al: MPI Technical report 157 about two-sample test pdf
- Gretton et al, JMLR , 2005 pdf
- Fukumizu et al, JMLR , 2004 pdf
- Kenji Fukumizu’s lecture slides: www
- Kenju Fukumizu’s tutorial at MLSS ’07: www
This talk is part of the Machine Learning Reading Group @ CUED series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
|