Lorenz Schmidt

Hi @sgrigory, > It should not be very difficult to add other kinds of Naive Bayes present in sklearn no not really, the question is rather how we want to...

In the context of generalized eigenvalue decomposition the LDA algorithm is a variant of PCA with orthogonal eigenvalues in different coordinates. I'm currently planing to add an implementation which has...

can we move this issue to the #22 and add general probabilistic PCA as well?

first one already happened in f353d4d6d2bd175c3c9c2b0e19aea3b7700a22be :smile:

to use the `Kernel` structure in the implementation of `Predict for T where T: PredictRef`

you can find the original paper here: https://web.stanford.edu/~hastie/Papers/LARS/LeastAngle_2002.pdf there is also a section in the [ELSII](https://web.stanford.edu/~hastie/Papers/ESLII.pdf) book on section 3.4.4 (p. 92) about LAR

any update here? This blocks bumping `ndarray = "0.14"` atm

> Hello, sorry for the silence, things are a bit complicated here and I don't have time to work on this right now (and probably for the next month as...

this seems to be broken again (perhaps a regression introduced in #290). The problem can be worked around by using `csmat_binop(a.view(), a.view(), |x, y| x.add(*y)) ` instead of this https://docs.rs/sprs/0.11.0/src/sprs/sparse/binop.rs.html#63...

For eigenvalue problems there is https://github.com/rust-ndarray/ndarray-linalg/pull/184 in the pipeline. It implements a blocked conjugated gradient algorithms in matrix-free fashion by accepting the linear operator as a closure [here](https://github.com/rust-ndarray/ndarray-linalg/pull/184/files#diff-83452e85d1e5900280690db07f27c688R142). A similar...