Fetching the paper…
Reading the bibliography…
We give the first provably efficient algorithm for learning a one hidden layer convolutional network with respect to a general class of (potentially overlapping) patches.
Efficient distribution-free learning of probabilistic concepts
Michael J Kearns and Robert E Schapire · 1990
Earlier work this paper cites.
Gershgorin circle theorem
Eric W Weisstein · 2003
Earlier work this paper cites.
Efficient learning of generalized linear and single index models with isotonic regression
Sham M Kakade, Varun Kanade, Ohad Shamir, and Adam Kalai · 2011
Earlier work this paper cites.
Reliably learning the relu in polynomial time
Surbhi Goel, Varun Kanade, Adam Klivans, and Justin Thaler · 2016
Earlier work this paper cites.
Symmetry-breaking convergence analysis of certain two-layered neural networks with relu nonlinearity
Yuandong Tian · 2016
Earlier work this paper cites.
Globally optimal gradient descent for a convnet with gaussian inputs
Alon Brutzkus and Amir Globerson · 2017
Earlier work this paper cites.
When is a convolutional filter easy to learn?
Simon S Du, Jason D Lee, and Yuandong Tian · 2017
Cited alongside, same era.
Gradient descent learns one-hidden-layer cnn: Don’t be afraid of spurious local minima
Simon S Du, Jason D Lee, Yuandong Tian, Barnabas Poczos, and Aarti Singh · 2017
Cited alongside, same era.
Eigenvalue decay implies polynomial-time learnability for neural networks
Surbhi Goel and Adam Klivans · 2017
Cited alongside, same era.
Learning depth-three neural networks in polynomial time
Surbhi Goel and Adam Klivans · 2017
Cited alongside, same era.
Learning one-hidden-layer neural networks with landscape design
Rong Ge, Jason Lee, and Tengyu Ma · 2017
Convergence analysis of two-layer neural networks with relu activation
Yuanzhi Li and Yang Yuan · 2017
Later among the works it cites.
Learning relus via gradient descent
Mahdi Soltanolkotabi · 2017
Later among the works it cites.
Electron-proton dynamics in deep learning
Qiuyi Zhang, Rina Panigrahy, Sushant Sachdeva, and Ali Rahimi · 2017
Later among the works it cites.
Learning non-overlapping convolutional neural networks with multiple kernels
Kai Zhong, Zhao Song, and Inderjit S Dhillon · 2017
Later among the works it cites.
Recovery guarantees for one-hidden-layer neural networks
Kai Zhong, Zhao Song, Prateek Jain, Peter L Bartlett, and Inderjit S Dhillon · 2017
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Cited alongside, same era.
Learning graphical models using multiplicative weights
Adam Klivans and Raghu Meka · 2017
Cited alongside, same era.