53 citations · 315 across the 37 of their papers we have counts for
Showing 2017Show all
2 papers · 1 filter
cs.DS2017★ 27 cited
Learning Neural Networks with Two Nonlinear Layers in Polynomial Time
Surbhi Goel, Adam Klivans
We give a polynomial-time algorithm for learning neural networks with one layer of sigmoids feeding into any Lipschitz, monotone activation function (e.g., sigmoid or ReLU). We mak…
cs.LG2017★ 7 cited
Eigenvalue Decay Implies Polynomial-Time Learnability for Neural Networks
Surbhi Goel, Adam Klivans
We consider the problem of learning function classes computed by neural networks with various activations (e.g. ReLU or Sigmoid), a task believed to be computationally intractable…