When Will Gradient Methods Converge to Max-margin Classifier under ReLU Models?

ICLR 2019 Tengyu XuYi ZhouKaiyi JiYingbin Liang

We study the implicit bias of gradient descent methods in solving a binary classification problem over a linearly separable dataset. The classifier is described by a nonlinear ReLU model and the objective function adopts the exponential loss function... (read more)

PDF Abstract ICLR 2019 PDF ICLR 2019 Abstract

Code


No code implementations yet. Submit your code now

Tasks


Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper