Christian Lorentzen

:rocket: @glemaitre 🎉 Thanks for this great addition many have been longing for. In a way, I like the explicit `FixedThresholdClassifier`. Out of curiosity: is there a path forward that...

@ogrisel @mathurinm @TomDLT @agramfort @rth might be interested as this seems to be new ground for GLM solvers, especially the multinomial logistic regression! It was a very stony path to...

While the [inclusion criteria](https://scikit-learn.org/stable/faq.html#what-are-the-inclusion-criteria-for-new-algorithms) are, strictly speaking, not (yet) fulfilled, I think that this approach adds value. There are, however, 2 critical questions - Where to stop: There are infinitely...

> Out of curiosity, have you tried to profile this to pinpoint the bottlenecks for both the multinomial and non-multinomial cases? For the multinomial/multiclass case, it clearly is `LDL.sqrt_D_Lt_matmul` and...

With the latest improvements it looks a bit better (btw `n_classes=12`) ### Sparse X (as above)  ### Dense X Added 24.02.2023  ### Conclusion So this solver can be...

Looking at the last plot, I wonder why the LMSR-based solver seems to slow down after the first 4 iterations, before it accelerates in the last two again. Perhaps, the...

@scikit-learn/core-devs This meeds a decision. Citation-wise, it is a bit on the boundary. I‘m personally inclined to include it as it is statistically sound and „the next best/simplest“ method after...

The remaining CI error will be automatically fixed by setting scipy>=1.4, see https://github.com/scipy/scipy/issues/7396. Note that the transpose is only taken in a few tests, the solver itself works fine with...

@GaelVaroquaux Could you expand a bit? Do you argue against inclusion?

CI all 🟢 again.