English
Related papers

Related papers: On the Complexity of Learning Neural Networks

200 papers

Even though probabilistic treatments of neural networks have a long history, they have not found widespread use in practice. Sampling approaches are often too slow already for simple networks. The size of the inputs and the depth of typical…

Computer Vision and Pattern Recognition · Computer Science 2018-05-30 Jochen Gast , Stefan Roth

We contribute to a better understanding of the class of functions that can be represented by a neural network with ReLU activations and a given architecture. Using techniques from mixed-integer optimization, polyhedral theory, and tropical…

Machine Learning · Computer Science 2024-07-18 Christoph Hertrich , Amitabh Basu , Marco Di Summa , Martin Skutella

Can a neural network minimizing cross-entropy learn linearly separable data? Despite progress in the theory of deep learning, this question remains unsolved. Here we prove that SGD globally optimizes this learning problem for a two-layer…

Machine Learning · Computer Science 2021-07-29 Roei Sarussi , Alon Brutzkus , Amir Globerson

Universal approximation theorem suggests that a shallow neural network can approximate any function. The input to neurons at each layer is a weighted sum of previous layer neurons and then an activation is applied. These activation…

Machine Learning · Computer Science 2020-10-30 Bhaavan Goel

It is well-known that neural networks are computationally hard to train. On the other hand, in practice, modern day neural networks are trained efficiently using SGD and a variety of tricks that include different activation functions (e.g.…

Machine Learning · Computer Science 2014-10-29 Roi Livni , Shai Shalev-Shwartz , Ohad Shamir

Neural networks have been successfully used for classification tasks in a rapidly growing number of practical applications. Despite their popularity and widespread use, there are still many aspects of training and classification that are…

Machine Learning · Computer Science 2016-05-03 Ewout van den Berg

This paper studies the approximation capacity of neural networks with an arbitrary activation function and with norm constraint on the weights. Upper and lower bounds on the approximation error of these networks are computed for smooth…

Numerical Analysis · Mathematics 2025-12-24 Francesco Paolo Maiale , Anastasiia Trofimova , Arturo De Marinis

Understanding the generalization properties of neural networks on simple input-output distributions is key to explaining their performance on real datasets. The classical teacher-student setting, where a network is trained on data generated…

Disordered Systems and Neural Networks · Physics 2026-03-26 Rodrigo Pérez Ortiz , Gibbs Nwemadji , Jean Barbier , Federica Gerace , Alessandro Ingrosso , Clarissa Lauditi , Enrico M. Malatesta

There is plenty of theoretical and empirical evidence that depth of neural networks is a crucial ingredient for their success. However, network training becomes more difficult with increasing depth and training of very deep networks remains…

Machine Learning · Computer Science 2015-11-04 Rupesh Kumar Srivastava , Klaus Greff , Jürgen Schmidhuber

The fundamental learning theory behind neural networks remains largely open. What classes of functions can neural networks actually learn? Why doesn't the trained network overfit when it is overparameterized? In this work, we prove that…

Machine Learning · Computer Science 2020-06-02 Zeyuan Allen-Zhu , Yuanzhi Li , Yingyu Liang

We show that under some widely believed assumptions, there are no higher-order algorithms for basic tasks in computational mathematics such as: Computing integrals with neural network integrands, computing solutions of a Poisson equation…

Numerical Analysis · Mathematics 2025-05-26 Michael Feischl , Fabian Zehetgruber

We consider functions from the real numbers to the real numbers, output by a neural network with 1 hidden activation layer, arbitrary width, and ReLU activation function. We assume that the parameters of the neural network are chosen…

Machine Learning · Computer Science 2023-04-20 David Holmes

Neural networks are one of the most popularly used methods in machine learning and artificial intelligence nowadays. Due to the universal approximation theorem (Hornik et al. (1989)), a neural network with one hidden layer can approximate…

Statistics Theory · Mathematics 2019-09-18 Xiaoxi Shen , Chang Jiang , Lyudmila Sakhanenko , Qing Lu

It is widely conjectured that the reason that training algorithms for neural networks are successful because all local minima lead to similar performance, for example, see (LeCun et al., 2015, Choromanska et al., 2015, Dauphin et al.,…

Machine Learning · Computer Science 2018-03-06 Shiyu Liang , Ruoyu Sun , Yixuan Li , R. Srikant

We investigate the complexity of the reachability problem for (deep) neural networks: does it compute valid output given some valid input? It was recently claimed that the problem is NP-complete for general neural networks and…

Computational Complexity · Computer Science 2026-04-08 Marco Sälzer , Martin Lange

In this short note, we give an elementary proof of a universal approximation theorem for neural networks with three hidden layers and increasing, continuous, bounded activation function. The result is weaker than the best known results, but…

Machine Learning · Computer Science 2024-12-24 Chris Monico

Neural networks are a powerful class of functions that can be trained with simple gradient descent to achieve state-of-the-art performance on a variety of applications. Despite their practical success, there is a paucity of results that…

Machine Learning · Computer Science 2017-03-06 Bo Xie , Yingyu Liang , Le Song

We perform an experimental study of the dynamics of Stochastic Gradient Descent (SGD) in learning deep neural networks for several real and synthetic classification tasks. We show that in the initial epochs, almost all of the performance…

Machine Learning · Computer Science 2019-05-29 Preetum Nakkiran , Gal Kaplun , Dimitris Kalimeris , Tristan Yang , Benjamin L. Edelman , Fred Zhang , Boaz Barak

Training neural networks is a challenging non-convex optimization problem, and backpropagation or gradient descent can get stuck in spurious local optima. We propose a novel algorithm based on tensor decomposition for guaranteed training of…

Machine Learning · Computer Science 2016-01-13 Majid Janzamin , Hanie Sedghi , Anima Anandkumar

We analyze multi-layer neural networks in the asymptotic regime of simultaneously (A) large network sizes and (B) large numbers of stochastic gradient descent training iterations. We rigorously establish the limiting behavior of the…

Probability · Mathematics 2021-04-06 Justin Sirignano , Konstantinos Spiliopoulos