When Do Neural Networks Outperform Kernel Methods

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

When Do Neural Networks Outperform Kernel
             Methods?

     Behrooz Ghorbani, Song Mei, Theodor Misiakiewicz, Andrea Montanari§

                         Abstract
      For a certain scaling of the initialization of stochastic gradient descent (SGD), wide
      neural networks (NN) have been shown to be well approximated by reproducing
      kernel Hilbert space (RKHS) methods. Recent empirical work showed that, for
      some classification tasks, RKHS methods can replace NNs wit ...

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏0 回帖

关键词：Outperform Networks Methods Perform network