Ronan Perry
Ronan Perry
Make a module with the various rank selection methods (ZG, explained variance, wedin bounds, etc) that get used in all the decomposition methods. Would be helpful to standardize that as...
Currently are two functions `check_Xs_y` and `check_Xs_y_nan_allowed` in `mvlearn.utils.utils.py`. Should be better addressed with a `nan_allowed` parameter in `check_Xs_y`. Need to update those functions and all instances of it being...
Implement the algorithm featured in: Crainiceanu, Ciprian M., et al. "Population value decomposition, a framework for the analysis of image populations." Journal of the American Statistical Association 106.495 (2011): 775-790....
Add ability to pass in custom kernel.
## Desired Behavior Currently, the signal dimensions of the gaussian mixture are deterministically determined from the latent positions. Additional white noise should be added to better mask the truth. Then...
## Problem Many old tutorials use plotting functions defined in the notebook rather than the plotting functions in the package (i.e. MVMDS) ## Solution Upgrade tutorials to use `crossviews_plot` from...
Currently no great way of telling the best number of components to use from KCCA. Currently the user specifies a number. Consider otherwise calculating all the eigenvalues and thresholding a...
List of repos/packages here to consider implementing. https://github.com/mikelove/awesome-multi-omics
500+ citations, consider investigating. "GMA is a supervised extension of Canonical Correlational Analysis (CCA), which is useful for cross-view classification and retrieval. The proposed approach is general and has the...
Deep Canonical Correlation Analysis: https://arxiv.org/abs/1702.02519 https://github.com/VahidooX/DeepCCA