NeurIPS 2019
Sun Dec 8th through Sat the 14th, 2019 at Vancouver Convention Center
Paper ID:4827
Title:What Can ResNet Learn Efficiently, Going Beyond Kernels?

There has been many theoretical papers studying neural nets in the setting that they behave like kernels. This work shows a clear example of functions that 1) cannot be learned in kernel setting 2) a neural net can learn it efficiently. Even though limitations of kernel methods are known among practitioners, this result is significant as it characterizes these limitations in a provable way. Therefore, I recommend acceptance.