Tight Hardness Results for Training Depth-2 ReLU Networks

27 November 2020

Papers citing "Tight Hardness Results for Training Depth-2 ReLU Networks"

29 / 29 papers shown

Title
The Computational Complexity of Counting Linear Regions in ReLU Neural Networks Moritz Stargalla Christoph Hertrich Daniel Reichman MLT 35 0 0 22 May 2025
On the Expressiveness of Rational ReLU Neural Networks With Bounded Depth Gennadiy Averkov Christopher Hojny Maximilian Merkert 135 4 0 10 Feb 2025
Generalizability of Memorization Neural Networks Lijia Yu Xiao-Shan Gao Lijun Zhang Yibo Miao 99 1 0 01 Nov 2024
Absence of Closed-Form Descriptions for Gradient Flow in Two-Layer Narrow Networks Yeachan Park AI4CE 112 0 0 15 Aug 2024
Linear Bellman Completeness Suffices for Efficient Online Reinforcement Learning with Few Actions Noah Golowich Ankur Moitra OffRL 68 1 0 17 Jun 2024
Convex Relaxations of ReLU Neural Networks Approximate Global Optima in Polynomial Time Sungyoon Kim Mert Pilanci 191 4 0 06 Feb 2024
Polynomial-Time Solutions for ReLU Network Training: A Complexity Classification via Max-Cut and Zonotopes Yifei Wang Mert Pilanci 74 3 0 18 Nov 2023
Dissecting Chain-of-Thought: Compositionality through In-Context Filtering and Learning Yingcong Li Kartik K. Sreenivasan Angeliki Giannou Dimitris Papailiopoulos Samet Oymak LRM 113 18 0 30 May 2023
Complexity of Neural Network Training and ETR: Extensions with Effectively Continuous Functions Teemu Hankala Miika Hannula J. Kontinen Jonni Virtema 46 5 0 19 May 2023
When Deep Learning Meets Polyhedral Theory: A Survey Joey Huchette Gonzalo Muñoz Thiago Serra Calvin Tsay AI4CE 160 37 0 29 Apr 2023
Training Neural Networks is NP-Hard in Fixed Dimension Vincent Froese Christoph Hertrich 110 10 0 29 Mar 2023
Finite-Sample Analysis of Learning High-Dimensional Single ReLU Neuron Jingfeng Wu Difan Zou Zixiang Chen Vladimir Braverman Quanquan Gu Sham Kakade 132 7 0 03 Mar 2023
Lower Bounds on the Depth of Integral ReLU Neural Networks via Lattice Polytopes Christian Haase Christoph Hertrich Georg Loho 79 22 0 24 Feb 2023
Computational Complexity of Learning Neural Networks: Smoothness and Degeneracy Amit Daniely Nathan Srebro Gal Vardi 96 5 0 15 Feb 2023
A Combinatorial Perspective on the Optimization of Shallow ReLU Networks Michael Matena Colin Raffel 32 1 0 01 Oct 2022
$Training Fully Connected Neural Networks is $\exists\mathbb{R}$-Complete$ Training Fully Connected Neural Networks is $\exists\mathbb{R}$ -Complete Daniel Bertschinger Christoph Hertrich Paul Jungeblut Tillmann Miltzow Simon Weber OffRL 123 30 0 04 Apr 2022
Neural networks with linear threshold activations: structure and algorithms Sammy Khalife Hongyu Cheng A. Basu 105 16 0 15 Nov 2021
Path Regularization: A Convexity and Sparsity Inducing Regularization for Parallel ReLU Networks Tolga Ergen Mert Pilanci 94 16 0 18 Oct 2021
Robust Generalization of Quadratic Neural Networks via Function Identification Kan Xu Hamsa Bastani Osbert Bastani OOD 67 8 0 22 Sep 2021
Early-stopped neural networks are consistent Ziwei Ji Justin D. Li Matus Telgarsky 85 37 0 10 Jun 2021
Learning a Single Neuron with Bias Using Gradient Descent Gal Vardi Gilad Yehudai Ohad Shamir MLT 84 17 0 02 Jun 2021
Towards Lower Bounds on the Depth of ReLU Neural Networks Christoph Hertrich A. Basu M. D. Summa M. Skutella 108 43 0 31 May 2021
The Computational Complexity of ReLU Network Training Parameterized by Data Dimensionality Vincent Froese Christoph Hertrich R. Niedermeier 67 24 0 18 May 2021
$Training Neural Networks is $\exists\mathbb R$-complete$ Training Neural Networks is $\exists\mathbb R$ -complete Mikkel Abrahamsen Linda Kleist Tillmann Miltzow 21 1 0 19 Feb 2021
ReLU Neural Networks of Polynomial Size for Exact Maximum Flow Computation Christoph Hertrich Leon Sering 111 10 0 12 Feb 2021
From Local Pseudorandom Generators to Hardness of Learning Amit Daniely Gal Vardi 129 32 0 20 Jan 2021
Algorithms and SQ Lower Bounds for PAC Learning One-Hidden-Layer ReLU Networks Ilias Diakonikolas D. Kane Vasilis Kontonis Nikos Zarifis 76 66 0 22 Jun 2020
Provably Good Solutions to the Knapsack Problem via Neural Networks of Bounded Size Christoph Hertrich M. Skutella 99 22 0 28 May 2020
Principled Deep Neural Network Training through Linear Programming D. Bienstock Gonzalo Muñoz Sebastian Pokutta 89 25 0 07 Oct 2018