No article text was recorded for this version.
computational complexity of training
Version 2 of 245 papers76 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Book Review:Neural Network Design and the Complexity of Learning, by J. Stephen Judd. Cambridge, MA: MIT Press, 1990
- Blog: Training Neural Networks is NP-Hard in Fixed Dimension
- Blog: Complexity of training ReLU neural network
- Blog: Training a 3-Node Neural Network is NP-Complete
- Blog: Training Deep Neural Networks with Constrained Learning Parameters
- Blog: Complexity Issues in Neural Computation and Learning
- Blog: Mathematical Aspects of Neural Networks
- Blog: Training Neural Networks is ER-complete
- Blog: Training Neural Networks is NP-Hard in Fixed Dimension
- Blog: Training Fully Connected Neural Networks is ∃R-Complete
- Blog: Learning Two Layer Rectified Neural Networks in Polynomial Time
- Blog: On the Complexity of Learning Neural Networks
- Blog: Agnostic PAC-Learning of Functions on Analog Neural Nets
- Blog: The Computational Complexity of ReLU Network Training Parameterized by Data Dimensionality
- Blog: Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs
- Blog: A Combinatorial Perspective on the Optimization of Shallow ReLU Networks
- Blog: On the Infeasibility of Training Neural Networks with Small Squared Errors
- Blog: Optimization-Based Separations for Neural Networks
- Blog: Tight Hardness Results for Training Depth-2 ReLU Networks
- Blog: l 1 -regularized neural networks are improperly learnable in polynomial time
- Blog: Statistical-Query Lower Bounds via Functional Gradients
- Blog: The Computational Complexity of Training ReLU(s)
- Blog: Complexity of Neural Network Training and ETR: Extensions with Effectively Continuous Functions
- Blog: Convex Relaxations of Convolutional Neural Nets
- Blog: Vector-output ReLU Neural Network Problems are Copositive Programs: Convex Analysis of Two Layer Networks and Polynomial-time Algorithms
- Blog: Principled deep neural network training through linear programming
- Blog: Training Neural Networks is ER-complete
- Blog: Provable training of a ReLU gate with an iterative non-gradient algorithm
- Blog: Constructing Hidden Units Using Examples and Queries
- Blog: On the Learnability of Fully-Connected Neural Networks
- Blog: Optimality and NP-Hardness of Transformers in Learning Markovian Dynamical Functions
- Blog: Training a sigmoidal network is difficult
- Blog: Training Quantized Neural Networks to Global Optimality via Semidefinite Programming
- Blog: Gradient Descent Finds Global Minima for Generalizable Deep Neural Networks of Practical Sizes
- Blog: Eigenvalue Decay Implies Polynomial-Time Learnability for Neural Networks
- Blog: New Complexity-Theoretic Frontiers of Tractability for Neural Network Training
- Blog: On the Non-Existence of a Universal Learning Algorithm for Recurrent Neural Networks
- Blog: Applying statistical learning theory to deep learning
- Blog: Hardness of Learning Neural Networks with Natural Weights
- Blog: On the Hardness of Training Deep Neural Networks Discretely
- Blog: Globally Optimal Training of Generalized Polynomial Neural Networks with Nonlinear Spectral Methods
- Blog: On the Optimality of Incremental Neural Network Algorithms
- Blog: Provable Bounds for Learning Some Deep Representations
- Blog: Polynomial-Time Solutions for ReLU Network Training: A Complexity Classification via Max-Cut and Zonotopes
- Blog: On Learning µ-Perceptron Networks with Binary Weights
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_computational_complexity_of_training_a4c69be1,
title = {computational complexity of training},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/computational-complexity-of-training/rdr_a4c69be1b6b94aabb746a59ed4fe53f3},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 2, frozen text):
@misc{lacuna_computational_complexity_of_training_a4c69be1_v2,
title = {computational complexity of training},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/computational-complexity-of-training/rdr_a4c69be1b6b94aabb746a59ed4fe53f3/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}