Understanding Global Loss Landscape of One-hidden-layer ReLU Networks, Part 1: Theory

12 February 2020

Papers citing "Understanding Global Loss Landscape of One-hidden-layer ReLU Networks, Part 1: Theory"

15 / 15 papers shown

Title
Elimination of All Bad Local Minima in Deep Learning Kenji Kawaguchi L. Kaelbling 72 44 0 02 Jan 2019
Stochastic Gradient Descent Optimizes Over-parameterized Deep ReLU Networks Difan Zou Yuan Cao Dongruo Zhou Quanquan Gu ODL 185 448 0 21 Nov 2018
Depth with Nonlinearity Creates No Bad Local Minima in ResNets Kenji Kawaguchi Yoshua Bengio ODL 78 64 0 21 Oct 2018
On the loss landscape of a class of deep neural networks with no bad local valleys Quynh N. Nguyen Mahesh Chandra Mukkamala Matthias Hein 75 87 0 27 Sep 2018
Are ResNets Provably Better than Linear Predictors? Ohad Shamir 55 54 0 18 Apr 2018
On the Power of Over-parametrization in Neural Networks with Quadratic Activation S. Du Jason D. Lee 178 271 0 03 Mar 2018
Essentially No Barriers in Neural Network Energy Landscape Felix Dräxler K. Veschgini M. Salmhofer Fred Hamprecht MoMe 111 432 0 02 Mar 2018
Learning One-hidden-layer Neural Networks with Landscape Design Rong Ge Jason D. Lee Tengyu Ma MLT 196 262 0 01 Nov 2017
Porcupine Neural Networks: (Almost) All Local Optima are Global Soheil Feizi Hamid Javadi Jesse M. Zhang David Tse 71 36 0 05 Oct 2017
Theoretical insights into the optimization landscape of over-parameterized shallow neural networks Mahdi Soltanolkotabi Adel Javanmard Jason D. Lee 172 419 0 16 Jul 2017
Depth Creates No Bad Local Minima Haihao Lu Kenji Kawaguchi ODL FAtt 71 121 0 27 Feb 2017
Identity Matters in Deep Learning Moritz Hardt Tengyu Ma OOD 84 398 0 14 Nov 2016
Topology and Geometry of Half-Rectified Network Optimization C. Freeman Joan Bruna 194 235 0 04 Nov 2016
Matrix Completion has No Spurious Local Minimum Rong Ge Jason D. Lee Tengyu Ma 105 599 0 24 May 2016
Qualitatively characterizing neural network optimization problems Ian Goodfellow Oriol Vinyals Andrew M. Saxe ODL 108 522 0 19 Dec 2014