Alexey Stukalov
Alexey Stukalov
### Is there an existing issue for this? - [X] I have searched the existing issues ### OS/Web Information - Web Browser: Chrome 103 - Local OS: Windows 10 -...
In master the subplot margins are _subtracted_ from the given subplot width/heights. Since top-left subplot should start in (0,1) and bottom-right should end at (1,0), the left margin is not...
The PR extracts `merge_plots()` function from the `subplot()` function, so that `subplot()` only checks the `plots` argument and defines how the plots should be layed out in the merged result....
This is a small cleanup to the `subplot()` grid layout logic: when defining the new domains of Y axis, `get_domains()` sets the new `ystart` > `yend`, but later in `subplot()`/`reposition()`...
#### Summary: Add Laplace (*double exponential*) family to the list of supported likelihood distributions. #### Description: Laplacian distribution allows modeling the noise with heavy tails. Since its maximum likelihood estimators...
Fixes a few issues I have encountered when running `normalized_cut()`: * sometimes `eigs()` returns less eigenvectors than requested, even less than 2. In the latter case the algorithm now would...
Unless there are better ideas, I suggest to rename it into `variatinfo()`, because `varinfo` really sounds like some information about a variable. What should be the roadmap for renaming? Introduce...
The PR improves the performance of *ECDF* and adds interpolation. * The major problem with the current code is that in the weighted case the partial sums have to be...
In my case I saw a x4 speedup for a function of 530 variables.
The calculation of the gradient from a multivariate normal prior involves left-division by a triangular matrix. Currently, when the covariance matrix is fixed, and the random vector depends on model...