Optimization Landscape and Expressivity of Deep CNNs

30 October 2017

Matthias Hein

Papers citing "Optimization Landscape and Expressivity of Deep CNNs"

49 / 49 papers shown

Title
When is a Convolutional Filter Easy To Learn? S. Du Jason D. Lee Yuandong Tian MLT 53 130 0 18 Sep 2017
Learning Neural Networks with Two Nonlinear Layers in Polynomial Time Surbhi Goel Adam R. Klivans 56 52 0 18 Sep 2017
Global optimality conditions for deep neural networks Chulhee Yun S. Sra Ali Jadbabaie 136 118 0 08 Jul 2017
Recovery Guarantees for One-hidden-layer Neural Networks Kai Zhong Zhao Song Prateek Jain Peter L. Bartlett Inderjit S. Dhillon MLT 141 336 0 10 Jun 2017
Convergence Analysis of Two-layer Neural Networks with ReLU Activation Yuanzhi Li Yang Yuan MLT 126 650 0 28 May 2017
Learning ReLUs via Gradient Descent Mahdi Soltanolkotabi MLT 68 181 0 10 May 2017
The loss surface of deep and wide neural networks Quynh N. Nguyen Matthias Hein ODL 125 284 0 26 Apr 2017
Failures of Gradient-Based Deep Learning Shai Shalev-Shwartz Ohad Shamir Shaked Shammah ODL UQCV 79 200 0 23 Mar 2017
An Analytical Formula of Population Gradient for two-layered ReLU network and its Applications in Convergence and Critical Point Analysis Yuandong Tian MLT 155 216 0 02 Mar 2017
Understanding Synthetic Gradients and Decoupled Neural Interfaces Wojciech M. Czarnecki G. Swirszcz Max Jaderberg Simon Osindero Oriol Vinyals Koray Kavukcuoglu 57 82 0 01 Mar 2017
Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs Alon Brutzkus Amir Globerson MLT 139 313 0 26 Feb 2017
Exponentially vanishing sub-optimal local minima in multilayer neural networks Daniel Soudry Elad Hoffer 134 97 0 19 Feb 2017
Identity Matters in Deep Learning Moritz Hardt Tengyu Ma OOD 81 399 0 14 Nov 2016
Understanding deep learning requires rethinking generalization Chiyuan Zhang Samy Bengio Moritz Hardt Benjamin Recht Oriol Vinyals HAI 304 4,623 0 10 Nov 2016
Topology and Geometry of Half-Rectified Network Optimization C. Freeman Joan Bruna 165 235 0 04 Nov 2016
Why and When Can Deep -- but Not Shallow -- Networks Avoid the Curse of Dimensionality: a Review T. Poggio H. Mhaskar Lorenzo Rosasco Brando Miranda Q. Liao 97 578 0 02 Nov 2016
Depth-Width Tradeoffs in Approximating Natural Functions with Neural Networks Itay Safran Ohad Shamir 77 174 0 31 Oct 2016
Globally Optimal Training of Generalized Polynomial Neural Networks with Nonlinear Spectral Methods A. Gautier Quynh N. Nguyen Matthias Hein 101 32 0 28 Oct 2016
Why Deep Neural Networks for Function Approximation? Shiyu Liang R. Srikant 101 385 0 13 Oct 2016
Xception: Deep Learning with Depthwise Separable Convolutions François Chollet MDE BDL PINN 1.1K 14,518 0 07 Oct 2016
Understanding intermediate layers using linear classifier probes Guillaume Alain Yoshua Bengio FAtt 121 941 0 05 Oct 2016
Error bounds for approximations with deep ReLU networks Dmitry Yarotsky 169 1,226 0 03 Oct 2016
Distribution-Specific Hardness of Learning Neural Networks Ohad Shamir 68 116 0 05 Sep 2016
Deep vs. shallow networks : An approximation theory perspective H. Mhaskar T. Poggio 132 342 0 10 Aug 2016
On the Expressive Power of Deep Neural Networks M. Raghu Ben Poole Jon M. Kleinberg Surya Ganguli Jascha Narain Sohl-Dickstein 61 786 0 16 Jun 2016
ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation Adam Paszke Abhishek Chaurasia Sangpil Kim Eugenio Culurciello SSeg 305 2,077 0 07 Jun 2016
Deep Learning without Poor Local Minima Kenji Kawaguchi ODL 190 923 0 23 May 2016
Convolutional Rectifier Networks as Generalized Tensor Decompositions Nadav Cohen Amnon Shashua 60 153 0 01 Mar 2016
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size F. Iandola Song Han Matthew W. Moskewicz Khalid Ashraf W. Dally Kurt Keutzer 134 7,465 0 24 Feb 2016
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning Christian Szegedy Sergey Ioffe Vincent Vanhoucke Alexander A. Alemi 346 14,223 0 23 Feb 2016
Benefits of depth in neural networks Matus Telgarsky 324 608 0 14 Feb 2016
The Power of Depth for Feedforward Neural Networks Ronen Eldan Ohad Shamir 186 732 0 12 Dec 2015
Deep Residual Learning for Image Recognition Kaiming He Xinming Zhang Shaoqing Ren Jian Sun MedIm 1.8K 193,426 0 10 Dec 2015
Rethinking the Inception Architecture for Computer Vision Christian Szegedy Vincent Vanhoucke Sergey Ioffe Jonathon Shlens Z. Wojna 3DV BDL 659 27,303 0 02 Dec 2015
Representation Benefits of Deep Feedforward Networks Matus Telgarsky 70 242 0 27 Sep 2015
Global Optimality in Tensor Factorization, Deep Learning, and Beyond B. Haeffele René Vidal 156 150 0 24 Jun 2015
Understanding Neural Networks Through Deep Visualization J. Yosinski Jeff Clune Anh Totti Nguyen Thomas J. Fuchs Hod Lipson FAtt AI4CE 122 1,871 0 22 Jun 2015
Qualitatively characterizing neural network optimization problems Ian Goodfellow Oriol Vinyals Andrew M. Saxe ODL 103 522 0 19 Dec 2014
Provable Methods for Training Neural Networks with Sparse Connectivity Hanie Sedghi Anima Anandkumar 59 64 0 08 Dec 2014
The Loss Surfaces of Multilayer Networks A. Choromańska Mikael Henaff Michaël Mathieu Gerard Ben Arous Yann LeCun ODL 249 1,196 0 30 Nov 2014
Understanding Deep Image Representations by Inverting Them Aravindh Mahendran Andrea Vedaldi FAtt 107 1,963 0 26 Nov 2014
How transferable are features in deep neural networks? J. Yosinski Jeff Clune Yoshua Bengio Hod Lipson OOD 188 8,321 0 06 Nov 2014
On the Computational Efficiency of Training Neural Networks Roi Livni Shai Shalev-Shwartz Ohad Shamir 119 479 0 05 Oct 2014
Going Deeper with Convolutions Christian Szegedy Wei Liu Yangqing Jia P. Sermanet Scott E. Reed Dragomir Anguelov D. Erhan Vincent Vanhoucke Andrew Rabinovich 388 43,589 0 17 Sep 2014
Very Deep Convolutional Networks for Large-Scale Image Recognition Karen Simonyan Andrew Zisserman FAtt MDE 1.3K 100,213 0 04 Sep 2014
Identifying and attacking the saddle point problem in high-dimensional non-convex optimization Yann N. Dauphin Razvan Pascanu Çağlar Gülçehre Kyunghyun Cho Surya Ganguli Yoshua Bengio ODL 121 1,383 0 10 Jun 2014
On the Number of Linear Regions of Deep Neural Networks Guido Montúfar Razvan Pascanu Kyunghyun Cho Yoshua Bengio 86 1,253 0 08 Feb 2014
On the number of response regions of deep feed forward networks with piece-wise linear activations Razvan Pascanu Guido Montúfar Yoshua Bengio FAtt 111 257 0 20 Dec 2013
Visualizing and Understanding Convolutional Networks Matthew D. Zeiler Rob Fergus FAtt SSL 443 15,861 0 12 Nov 2013