Typically algorithms for logistic regression have an iterative aspect since the problem does not admit a closed form solution. By extension, most iterative algorithms (gradient descent etc.) for logistic regression only admit additive error bounds to the loss function.

My question: does logistic regression admit any finite-factor multiplicative approximation algorithm with polynomial dependence on the dimension $d$ and the number of points $n$?


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.