Any idea what the preferred algorithm would be for linear SVMs with dense data? ... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

iskander on June 24, 2012 | parent | context | favorite | on: Which machine learning classifiers are fast enough...

Any idea what the preferred algorithm would be for linear SVMs with dense data? (other than SGD, of course)

ogrisel on June 24, 2012 [–]

SGD with averaging [1] :)

More seriously, SGD is pretty hard to beat for fitting linear models (SVM, logistic regression and other l1 penalized models with various loss functions) when the number of samples getting large.

[1] http://leon.bottou.org/projects/sgd

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact