tag:blogger.com,1999:blog-6141980.post4010260856817134743..comments2024-03-20T12:28:35.004-05:00Comments on Nuit Blanche: Generalization Properties of Learning with Random FeaturesIgorhttp://www.blogger.com/profile/17474880327699002140noreply@blogger.comBlogger1125tag:blogger.com,1999:blog-6141980.post-18757132079715945542016-03-04T07:52:06.923-06:002016-03-04T07:52:06.923-06:00Thanks for the post. in fact the incremental appro...Thanks for the post. in fact the incremental approach is just a plus. The number of features always plays the role of a regularization parameter. Most importantly this is the first proof that you can get optimal rates with a number of features smaller than the number of points. These results complement those for Nystrom like sampling http://arxiv.org/abs/1507.04717. pippohttps://www.blogger.com/profile/08558553488458829664noreply@blogger.com