vprusso
Compute the nonnegative rank of a nonnegative matrix
The nonnegative rank of a matrix, $A$, is defined as the smallest integer $k$ such that there exists nonnegative matrices $L$ and $R$ where $L$ is a $n \times k$ matrix and where $R$ is a $k \times m$ matrix such that $A = LR$.
https://core.ac.uk/download/pdf/82127902.pdf
Hey! Greetings @vprusso I think I can attempt solving this issue. Please assign me this.
@GauravR-Malik Same as my other comment, someone is already working on this issue.
https://github.com/vprusso/toqito/issues/652#issuecomment-2745294220
@GauravR-Malik Same as my other comment, someone is already working on this issue.
Sure. Didn't look at the time of commenting!
Hey @vprusso @purva-thakre, are there any existing functions in Toqito that I could use to implement this, or would it be better to build it from scratch? Also, would it be appropriate to use sklearn.decomposition.NMF for this task?
https://scikit-learn.org/stable/modules/generated/sklearn.decomposition.NMF.html
Hi @sahilsingh2402
are there any existing functions in Toqito that I could use to implement this, or would it be better to build it from scratch?
No, the point of this feature is to create a function that implements this. Maybe I'm confused by your question?
Also, would it be appropriate to use sklearn.decomposition.NMF for this task?
I don't see how this is related. The most relevant resource that describes how to implement this is already in the description of this issue.
This repository might be useful: here. It implements several iter-solvers that were developed after the base paper mentioned earlier and are claimed to be more efficient.
This repository might be useful: here. It implements several
iter-solversthat were developed after the base paper mentioned earlier and are claimed to be more efficient.
Good find, yep that may be quite useful for not just this task but likey some others as well. Cool, I hadn't stumbled on that before. Thanks for mentioning that!