Can one use non converged results from Logistic Regression?
-
01-11-2019 - |
Question
I'm running Logistic Regression on a dataset for a classification problem.
I used the model on the dataset when it was normalized and I had no problem with it converging.
Now, I wanted to see the results without feature normalization and I am getting the warning:
ConvergenceWarning: lbfgs failed to converge. Increase the number of iterations.
"of iterations.", ConvergenceWarning)
I've tried increasing the number of iterations and I have upped it to 8000 so far and am still getting the error.
I wanted to ask, is this error is critical? Because, I'm still getting my cross validated results even after the error. What exactly is convergence?
No correct solution
Licensed under: CC-BY-SA with attribution
Not affiliated with datascience.stackexchange