Is there any library that implements hard-SVM directly instead of soft-SVM? I looked at several libraries and they all seem to implement C-SVM or nu-SVM, something with the slack variables.
They probably don’t implement it because almost all datasets are not linearly separable. You could probably get a good approximate of the solution by setting C really high or nu really low. Also, linear hard margin SVMs can be solved relatively easily with quadratic programming (using say JuMP).
That’s what I figured. Thanks for the reply