$Training Fully Connected Neural Networks is $\exists\mathbb{R}$-Complete$

Training Fully Connected Neural Networks is $\exists\mathbb{R}$ -Complete

4 April 2022

Papers citing "Training Fully Connected Neural Networks is $\exists\mathbb{R}$-Complete"

48 / 48 papers shown

Title
When Deep Learning Meets Polyhedral Theory: A Survey Joey Huchette Gonzalo Muñoz Thiago Serra Calvin Tsay AI4CE 129 37 0 29 Apr 2023
Training Neural Networks is NP-Hard in Fixed Dimension Vincent Froese Christoph Hertrich 79 8 0 29 Mar 2023
Lower Bounds on the Depth of Integral ReLU Neural Networks via Lattice Polytopes Christian Haase Christoph Hertrich Georg Loho 48 22 0 24 Feb 2023
Hardness of Noise-Free Learning for Two-Hidden-Layer Neural Networks Sitan Chen Aravind Gollakota Adam R. Klivans Raghu Meka 49 30 0 10 Feb 2022
Neural networks with linear threshold activations: structure and algorithms Sammy Khalife Hongyu Cheng A. Basu 64 16 0 15 Nov 2021
On the Optimal Memorization Power of ReLU Neural Networks Gal Vardi Gilad Yehudai Ohad Shamir 43 32 0 07 Oct 2021
On minimal representations of shallow ReLU networks Steffen Dereich Sebastian Kassing FAtt 26 15 0 12 Aug 2021
On Classifying Continuous Constraint Satisfaction Problems Tillmann Miltzow R. F. Schmiermann 50 18 0 04 Jun 2021
Covering Polygons is Even Harder Mikkel Abrahamsen 65 25 0 04 Jun 2021
Towards Lower Bounds on the Depth of ReLU Neural Networks Christoph Hertrich A. Basu M. D. Summa M. Skutella 57 43 0 31 May 2021
The Computational Complexity of ReLU Network Training Parameterized by Data Dimensionality Vincent Froese Christoph Hertrich R. Niedermeier 28 24 0 18 May 2021
The Modern Mathematics of Deep Learning Julius Berner Philipp Grohs Gitta Kutyniok P. Petersen 41 116 0 09 May 2021
Sharp bounds for the number of regions of maxout networks and vertices of Minkowski sums Guido Montúfar Yue Ren Leon Zhang 37 41 0 16 Apr 2021
ReLU Neural Networks of Polynomial Size for Exact Maximum Flow Computation Christoph Hertrich Leon Sering 56 10 0 12 Feb 2021
Tight Hardness Results for Training Depth-2 ReLU Networks Surbhi Goel Adam R. Klivans Pasin Manurangsi Daniel Reichman 46 41 0 27 Nov 2020
Learning Deep ReLU Networks Is Fixed-Parameter Tractable Sitan Chen Adam R. Klivans Raghu Meka 49 37 0 28 Sep 2020
Provably Good Solutions to the Knapsack Problem via Neural Networks of Bounded Size Christoph Hertrich M. Skutella 69 21 0 28 May 2020
Approximation Schemes for ReLU Regression Ilias Diakonikolas Surbhi Goel Sushrut Karmalkar Adam R. Klivans Mahdi Soltanolkotabi 45 51 0 26 May 2020
Complexity of Linear Regions in Deep Networks Boris Hanin David Rolnick 37 230 0 25 Jan 2019
A Convergence Theory for Deep Learning via Over-Parameterization Zeyuan Allen-Zhu Yuanzhi Li Zhao Song AI4CE ODL 224 1,461 0 09 Nov 2018
Gradient Descent Finds Global Minima of Deep Neural Networks S. Du Jason D. Lee Haochuan Li Liwei Wang Masayoshi Tomizuka ODL 174 1,134 0 09 Nov 2018
Learning Two Layer Rectified Neural Networks in Polynomial Time Ainesh Bakshi Rajesh Jayaram David P. Woodruff NoLa 136 69 0 05 Nov 2018
Small ReLU networks are powerful memorizers: a tight analysis of memorization capacity Chulhee Yun S. Sra Ali Jadbabaie 84 118 0 17 Oct 2018
Principled Deep Neural Network Training through Linear Programming D. Bienstock Gonzalo Muñoz Sebastian Pokutta 42 24 0 07 Oct 2018
Complexity of Training ReLU Neural Network Digvijay Boob Santanu S. Dey Guanghui Lan 51 74 0 27 Sep 2018
Neural Tangent Kernel: Convergence and Generalization in Neural Networks Arthur Jacot Franck Gabriel Clément Hongler 238 3,191 0 20 Jun 2018
Tropical Geometry of Deep Neural Networks Liwen Zhang Gregory Naitzat Lek-Heng Lim 69 138 0 18 May 2018
Regularisation of Neural Networks by Enforcing Lipschitz Continuity Henry Gouk E. Frank Bernhard Pfahringer M. Cree 147 475 0 12 Apr 2018
Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions Quynh N. Nguyen Mahesh Chandra Mukkamala Matthias Hein MLT 63 56 0 28 Feb 2018
Learning One Convolutional Layer with Overlapping Patches Surbhi Goel Adam R. Klivans Raghu Meka MLT 71 80 0 07 Feb 2018
Lower bounds over Boolean inputs for deep neural networks with ReLU gates Anirbit Mukherjee A. Basu 54 21 0 08 Nov 2017
Bounding and Counting Linear Regions of Deep Neural Networks Thiago Serra Christian Tjandraatmadja Srikumar Ramalingam MLT 59 249 0 06 Nov 2017
Approximating Continuous Functions by ReLU Nets of Minimal Width Boris Hanin Mark Sellke 103 234 0 31 Oct 2017
Universal Function Approximation by Deep Neural Nets with Bounded Width and ReLU Activations Boris Hanin 55 353 0 09 Aug 2017
Gradient Descent Can Take Exponential Time to Escape Saddle Points S. Du Chi Jin Jason D. Lee Michael I. Jordan Barnabás Póczós Aarti Singh 54 244 0 29 May 2017
Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs Alon Brutzkus Amir Globerson MLT 145 313 0 26 Feb 2017
Reliably Learning the ReLU in Polynomial Time Surbhi Goel Varun Kanade Adam R. Klivans J. Thaler 78 126 0 30 Nov 2016
Understanding Deep Neural Networks with Rectified Linear Units R. Arora A. Basu Poorya Mianjy Anirbit Mukherjee PINN 143 640 0 04 Nov 2016
Depth-Width Tradeoffs in Approximating Natural Functions with Neural Networks Itay Safran Ohad Shamir 80 174 0 31 Oct 2016
Why Deep Neural Networks for Function Approximation? Shiyu Liang R. Srikant 107 385 0 13 Oct 2016
Error bounds for approximations with deep ReLU networks Dmitry Yarotsky 175 1,226 0 03 Oct 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
On Restricted Nonnegative Matrix Factorization D. Chistikov S. Kiefer Ines Marusic M. Shirmohammadi J. Worrell 59 14 0 23 May 2016
Benefits of depth in neural networks Matus Telgarsky 330 608 0 14 Feb 2016
The Power of Depth for Feedforward Neural Networks Ronen Eldan Ohad Shamir 195 732 0 12 Dec 2015
Representation Benefits of Deep Feedforward Networks Matus Telgarsky 76 242 0 27 Sep 2015
On the Number of Linear Regions of Deep Neural Networks Guido Montúfar Razvan Pascanu Kyunghyun Cho Yoshua Bengio 88 1,254 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