Open xiaoyuanzh opened 5 years ago
As for the high-dimensional data, maybe you can refer to this Direct Density-Ratio Estimation with Dimensionality Reduction via Hetero-Distributional Subspace Analysis .
The MATLAB code is provided here. Although I can't find the code of D3-HSA, I think that the performance of LHSS is good enough on high-dimensional data.
Hi. Thanks for sharing such wonderful package. I am wondering, whether it is possible to estimate the density ratio between two distribution of very high dimension, like 50 dimension?