Eigenvalue Decay Implies Polynomial-Time Learnability for Neural Networks

11 August 2017

Papers citing "Eigenvalue Decay Implies Polynomial-Time Learnability for Neural Networks"

10 / 10 papers shown

Title
On the Stochastic Stability of Deep Markov Models Ján Drgoňa Sayak Mukherjee Jiaxin Zhang Frank Liu M. Halappanavar BDL 25 5 0 08 Nov 2021
Learning Graph Neural Networks with Approximate Gradient Descent Qunwei Li Shaofeng Zou Leon Wenliang Zhong GNN 32 1 0 07 Dec 2020
Dissipative Deep Neural Dynamical Systems Ján Drgoňa Soumya Vasisht Aaron Tuor D. Vrabie 21 7 0 26 Nov 2020
From Boltzmann Machines to Neural Networks and Back Again Surbhi Goel Adam R. Klivans Frederic Koehler 21 5 0 25 Jul 2020
Frequency Bias in Neural Networks for Input of Non-Uniform Density Ronen Basri Meirav Galun Amnon Geifman David Jacobs Yoni Kasten S. Kritchman 42 183 0 10 Mar 2020
How Many Samples are Needed to Estimate a Convolutional or Recurrent Neural Network? S. Du Yining Wang Xiyu Zhai Sivaraman Balakrishnan Ruslan Salakhutdinov Aarti Singh SSL 21 57 0 21 May 2018
Improved Learning of One-hidden-layer Convolutional Neural Networks with Overlaps S. Du Surbhi Goel MLT 30 17 0 20 May 2018
Learning One Convolutional Layer with Overlapping Patches Surbhi Goel Adam R. Klivans Raghu Meka MLT 26 80 0 07 Feb 2018
The Loss Surfaces of Multilayer Networks A. Choromańska Mikael Henaff Michaël Mathieu Gerard Ben Arous Yann LeCun ODL 186 1,186 0 30 Nov 2014
Matrix Coherence and the Nystrom Method Ameet Talwalkar Afshin Rostamizadeh 96 88 0 09 Aug 2014