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

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

4 April 2022

Daniel Bertschinger

Christoph Hertrich

Tillmann Miltzow

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

16 / 16 papers shown

Title
Logical perspectives on learning statistical objects Aaron Anderson Michael Benedikt 49 0 0 01 Apr 2025
On the Expressiveness of Rational ReLU Neural Networks With Bounded Depth Gennadiy Averkov Christopher Hojny Maximilian Merkert 73 3 0 10 Feb 2025
On the Complexity of Identification in Linear Structural Causal Models Julian Dörfler Benito van der Zander Markus Bläser Maciej Liskiewicz CML 18 0 0 17 Jul 2024
Graph Neural Networks and Arithmetic Circuits Timon Barlag Vivian Holzapfel Laura Strieker Jonni Virtema H. Vollmer GNN 22 0 0 27 Feb 2024
Polynomial-Time Solutions for ReLU Network Training: A Complexity Classification via Max-Cut and Zonotopes Yifei Wang Mert Pilanci 11 3 0 18 Nov 2023
Complexity of Neural Network Training and ETR: Extensions with Effectively Continuous Functions Teemu Hankala Miika Hannula J. Kontinen Jonni Virtema 12 6 0 19 May 2023
When Deep Learning Meets Polyhedral Theory: A Survey Joey Huchette Gonzalo Muñoz Thiago Serra Calvin Tsay AI4CE 84 32 0 29 Apr 2023
Training Neural Networks is NP-Hard in Fixed Dimension Vincent Froese Christoph Hertrich 36 4 0 29 Mar 2023
Lower Bounds on the Depth of Integral ReLU Neural Networks via Lattice Polytopes Christian Haase Christoph Hertrich Georg Loho 11 12 0 24 Feb 2023
Neural networks with linear threshold activations: structure and algorithms Sammy Khalife Hongyu Cheng A. Basu 18 10 0 15 Nov 2021
On Classifying Continuous Constraint Satisfaction Problems Tillmann Miltzow R. F. Schmiermann 22 19 0 04 Jun 2021
Towards Lower Bounds on the Depth of ReLU Neural Networks Christoph Hertrich A. Basu M. D. Summa M. Skutella 19 31 0 31 May 2021
The Computational Complexity of ReLU Network Training Parameterized by Data Dimensionality Vincent Froese Christoph Hertrich R. Niedermeier 8 17 0 18 May 2021
ReLU Neural Networks of Polynomial Size for Exact Maximum Flow Computation Christoph Hertrich Leon Sering 8 10 0 12 Feb 2021
Provably Good Solutions to the Knapsack Problem via Neural Networks of Bounded Size Christoph Hertrich M. Skutella 36 12 0 28 May 2020
Benefits of depth in neural networks Matus Telgarsky 121 600 0 14 Feb 2016