I have tried to tuned the parameters with the function tune, but it took over 15 hours to tune this (and at that point I had to stop it):

tuned_parameters <- tune.svm(y~., 
                             data = train_set, 
                             gamma = 10^(-1:2), 
                             cost = 10^(-0.5:1))

My dataset is not even that large (40000 rows x 65 columns)

Do you know a faster way to tune the gamma and cost parameters?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.