On the Power of Over-parametrization in Neural Networks with Quadratic Activation

3 March 2018

Papers citing "On the Power of Over-parametrization in Neural Networks with Quadratic Activation"

17 / 67 papers shown

Title
Width Provably Matters in Optimization for Deep Linear Neural Networks S. Du Wei Hu 18 93 0 24 Jan 2019
On the Global Convergence of Imitation Learning: A Case for Linear Quadratic Regulator Qi Cai Mingyi Hong Yongxin Chen Zhaoran Wang 19 34 0 11 Jan 2019
Stochastic Gradient Descent Optimizes Over-parameterized Deep ReLU Networks Difan Zou Yuan Cao Dongruo Zhou Quanquan Gu ODL 27 446 0 21 Nov 2018
Gradient Descent Finds Global Minima of Deep Neural Networks S. Du J. Lee Haochuan Li Liwei Wang Masayoshi Tomizuka ODL 41 1,122 0 09 Nov 2018
Benefits of over-parameterization with EM Ji Xu Daniel J. Hsu A. Maleki 38 29 0 26 Oct 2018
Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernel Colin Wei J. Lee Qiang Liu Tengyu Ma 23 243 0 12 Oct 2018
A Convergence Analysis of Gradient Descent for Deep Linear Neural Networks Sanjeev Arora Nadav Cohen Noah Golowich Wei Hu 21 281 0 04 Oct 2018
Gradient Descent Provably Optimizes Over-parameterized Neural Networks S. Du Xiyu Zhai Barnabás Póczós Aarti Singh MLT ODL 38 1,250 0 04 Oct 2018
Universal Approximation with Quadratic Deep Networks Fenglei Fan Jinjun Xiong Ge Wang PINN 20 78 0 31 Jul 2018
Learning One-hidden-layer ReLU Networks via Gradient Descent Xiao Zhang Yaodong Yu Lingxiao Wang Quanquan Gu MLT 28 134 0 20 Jun 2018
Adding One Neuron Can Eliminate All Bad Local Minima Shiyu Liang Ruoyu Sun J. Lee R. Srikant 31 89 0 22 May 2018
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 18 57 0 21 May 2018
Improved Learning of One-hidden-layer Convolutional Neural Networks with Overlaps S. Du Surbhi Goel MLT 25 17 0 20 May 2018
Smoothed analysis for low-rank solutions to semidefinite programs in quadratic penalty form Srinadh Bhojanapalli Nicolas Boumal Prateek Jain Praneeth Netrapalli 23 42 0 01 Mar 2018
Benefits of depth in neural networks Matus Telgarsky 148 602 0 14 Feb 2016
Norm-Based Capacity Control in Neural Networks Behnam Neyshabur Ryota Tomioka Nathan Srebro 125 577 0 27 Feb 2015
The Loss Surfaces of Multilayer Networks A. Choromańska Mikael Henaff Michaël Mathieu Gerard Ben Arous Yann LeCun ODL 183 1,185 0 30 Nov 2014