-
I have been experimenting with `SGDRegressor` estimator to show if it is faster for large training set as compared to `Ridge` and **always finding that it is slower**.
This is quite opposite to [wh…
-
The current `STLSQ` implementation relies on Scikit-learn's [ridge regression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.ridge_regression.html#sklearn.linear_model.ridge_r…
-
(I never looked at this.)
Is there anything special that we can add for penalized estimators or can we apply the standard methods?
current case: multicollinearity measures and vif for ridge regr…
-
**Describe the bug**
When datasets are bigger than a certain size, ridge regression returns
```bash
Got CUSOLVER error 3 at /home/dante/rapids/cuml10-mst/mst-1015/cpp/src_prims/linalg/svd.h:67
…
-
variance inflation factor in outlier_influence uses the definition to calculate vif for one parameter instead of using linalg to calculate all of them at once
see my answer and example script which i…
-
Hi,
I tried to move some of the R code into Julia, and found the `ridge` regression in `MultivariateStats.jl` to replace `lm.ridge` in R. but it seems that the `lambda` in R is not exactly `r` in `…
babaq updated
4 years ago
-
(From https://github.com/scikit-learn/scikit-learn/pull/27800#issuecomment-1878709518 by @ogrisel)
The proposal/idea is to allow `y` to not be on the same device (and namespace?) as `X` when using …
-
[Reduced-rank regression](https://www.sciencedirect.com/science/article/pii/0047259X75900421) seems like a simple and fairly well-established technique. It could be implemented minimally by adding a `…
-
Baseline: Linear Regression
### Other Regressions (Matt)
Improve out of sample prediction accuracy by using regularization to avoid overfitting on the training set.
* Lasso regression
* Ridge r…
-
great code
but can you add code for intercept /bias to regressions
like
https://github.com/eriklindernoren/ML-From-Scratch/blob/master/mlfromscratch/examples/lasso_regression.py
for example you…