English
Related papers

Related papers: Size and Depth Separation in Approximating Benign …

200 papers

We propose semi-random features for nonlinear function approximation. The flexibility of semi-random feature lies between the fully adjustable units in deep learning and the random features used in kernel methods. For one hidden layer…

Machine Learning · Computer Science 2017-11-22 Kenji Kawaguchi , Bo Xie , Vikas Verma , Le Song

The standard Universal Approximation Theorem for operator neural networks (NNs) holds for arbitrary width and bounded depth. Here, we prove that operator NNs of bounded width and arbitrary depth are universal approximators for continuous…

Machine Learning · Computer Science 2021-09-24 Annan Yu , Chloé Becquey , Diana Halikias , Matthew Esmaili Mallory , Alex Townsend

Several recent works have shown separation results between deep neural networks, and hypothesis classes with inferior approximation capacity such as shallow networks or kernel classes. On the other hand, the fact that deep networks can…

Machine Learning · Computer Science 2021-07-20 Eran Malach , Gilad Yehudai , Shai Shalev-Shwartz , Ohad Shamir

Formal certification of Neural Networks (NNs) is crucial for ensuring their safety, fairness, and robustness. Unfortunately, on the one hand, sound and complete certification algorithms of ReLU-based NNs do not scale to large-scale NNs. On…

Machine Learning · Computer Science 2023-05-24 Haitham Khedr , Yasser Shoukry

While it is well-known that neural networks enjoy excellent approximation capabilities, it remains a big challenge to compute such approximations from point samples. Based on tools from Information-based complexity, recent work by Grohs and…

Machine Learning · Computer Science 2023-12-22 Ahmed Abdeljawad , Philipp Grohs

A recurrent neural network (RNN) is a widely used deep-learning network for dealing with sequential data. Imitating a dynamical system, an infinite-width RNN can approximate any open dynamical system in a compact domain. In general, deep…

Machine Learning · Statistics 2023-03-30 Chang hoon Song , Geonho Hwang , Jun ho Lee , Myungjoo Kang

The choice of activation function fundamentally shapes the representational capacity and parameter efficiency of deep neural networks, yet most widely used activations lack rigorous theoretical guarantees on these properties. We provide a…

Machine Learning · Computer Science 2026-05-14 Ibrahim Albool , Malak Gamal El-Din , Salma Elmalaki , Yasser Shoukry

The exact minimum width that allows for universal approximation of unbounded-depth networks is known only for ReLU and its variants. In this work, we study the minimum width of networks using general activation functions. Specifically, we…

Machine Learning · Computer Science 2025-04-11 Jonghyun Shin , Namjun Kim , Geonho Hwang , Sejun Park

Largest theoretical contribution to Neural Networks comes from VC Dimension which characterizes the sample complexity of classification model in a probabilistic view and are widely used to study the generalization error. So far in the…

Machine Learning · Computer Science 2024-09-05 Linu Pinto , Sasi Gopalan

We prove that the set of functions representable by ReLU neural networks with integer weights strictly increases with the network depth while allowing arbitrary width. More precisely, we show that $\lceil\log_2(n)\rceil$ hidden layers are…

Machine Learning · Computer Science 2023-02-27 Christian Haase , Christoph Hertrich , Georg Loho

We consider the problem of learning an unknown ReLU network with respect to Gaussian inputs and obtain the first nontrivial results for networks of depth more than two. We give an algorithm whose running time is a fixed polynomial in the…

Machine Learning · Computer Science 2020-09-29 Sitan Chen , Adam R. Klivans , Raghu Meka

We consider the problem of representing Boolean functions exactly by "sparse" linear combinations (over $\mathbb{R}$) of functions from some "simple" class ${\cal C}$. In particular, given ${\cal C}$ we are interested in finding…

Computational Complexity · Computer Science 2018-02-27 R. Ryan Williams

We investigate the approximation capabilities of dense neural networks. While universal approximation theorems establish that sufficiently large architectures can approximate arbitrary continuous functions if there are no restrictions on…

Machine Learning · Computer Science 2026-05-19 Levi Rauchwerger , Stefanie Jegelka , Ron Levie

Neural Networks (NNs) are the method of choice for building learning algorithms. Their popularity stems from their empirical success on several challenging learning problems. However, most scholars agree that a convincing theoretical…

Numerical Analysis · Mathematics 2021-01-01 Ronald DeVore , Boris Hanin , Guergana Petrova

This paper investigates the relationship between the universal approximation property of deep neural networks and topological characteristics of datasets. Our primary contribution is to introduce data topology-dependent upper bounds on the…

Machine Learning · Computer Science 2023-05-29 Sangmin Lee , Jong Chul Ye

In this paper, we construct neural networks with ReLU, sine and $2^x$ as activation functions. For general continuous $f$ defined on $[0,1]^d$ with continuity modulus $\omega_f(\cdot)$, we construct ReLU-sine-$2^x$ networks that enjoy an…

Machine Learning · Computer Science 2022-08-16 Yuling Jiao , Yanming Lai , Xiliang Lu , Fengru Wang , Jerry Zhijian Yang , Yuanyuan Yang

Deep neural networks (DNNs) have garnered significant attention in various fields of science and technology in recent years. Activation functions define how neurons in DNNs process incoming signals for them. They are essential for learning…

Machine Learning · Computer Science 2023-08-31 Jianfei Li , Han Feng , Ding-Xuan Zhou

We investigate to what extent it is possible to solve linear inverse problems with $ReLu$ networks. Due to the scaling invariance arising from the linearity, an optimal reconstruction function $f$ for such a problem is positive homogeneous,…

Machine Learning · Computer Science 2023-08-08 Stefan Bamberger , Reinhard Heckel , Felix Krahmer

We study the type of solutions to which stochastic gradient descent converges when used to train a single hidden-layer multivariate ReLU network with the quadratic loss. Our results are based on a dynamical stability analysis. In the…

Machine Learning · Computer Science 2023-07-03 Mor Shpigel Nacson , Rotem Mulayoff , Greg Ongie , Tomer Michaeli , Daniel Soudry

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