Why and when can deep-but not shallow-networks avoid the curse of dimensionality: a review

T Poggio, H Mhaskar, L Rosasco, B Miranda… - International Journal of …, 2017 - Springer
The paper reviews and extends an emerging body of theoretical results on deep learning
including the conditions under which it can be exponentially better than shallow learning. A …

Understanding deep learning (still) requires rethinking generalization

C Zhang, S Bengio, M Hardt, B Recht… - Communications of the …, 2021 - dl.acm.org
Despite their massive size, successful deep artificial neural networks can exhibit a
remarkably small gap between training and test performance. Conventional wisdom …

Error bounds for approximations with deep ReLU networks

D Yarotsky - Neural networks, 2017 - Elsevier
We study expressive power of shallow and deep neural networks with piece-wise linear
activation functions. We establish new rigorous upper and lower bounds for the network …

Nonparametric regression using deep neural networks with ReLU activation function

J Schmidt-Hieber - 2020 - projecteuclid.org
Nonparametric regression using deep neural networks with ReLU activation function Page 1
The Annals of Statistics 2020, Vol. 48, No. 4, 1875–1897 https://doi.org/10.1214/19-AOS1875 …

[BOOK][B] The nature of statistical learning theory

V Vapnik - 2013 - books.google.com
The aim of this book is to discuss the fundamental ideas which lie behind the statistical
theory of learning and generalization. It considers learning as a general problem of function …

[HTML][HTML] Universality of deep convolutional neural networks

DX Zhou - Applied and computational harmonic analysis, 2020 - Elsevier
Deep learning has been widely applied and brought breakthroughs in speech recognition,
computer vision, and many other domains. Deep neural network architectures and …

[BOOK][B] Neural network learning: Theoretical foundations

M Anthony, PL Bartlett - 2009 - dl.acm.org
This important work describes recent theoretical advances in the study of artificial neural
networks. It explores probabilistic models of supervised learning problems, and addresses …

Approximation theory of the MLP model in neural networks

A Pinkus - Acta numerica, 1999 - cambridge.org
In this survey we discuss various approximation-theoretic problems that arise in the
multilayer feedforward perceptron (MLP) model in neural networks. The MLP model is one of …

Regularization theory and neural networks architectures

F Girosi, M Jones, T Poggio - Neural computation, 1995 - ieeexplore.ieee.org
We had previously shown that regularization principles lead to approximation schemes that
are equivalent to networks with one layer of hidden units, called regularization networks. In …

Graph neural networks exponentially lose expressive power for node classification

K Oono, T Suzuki - arxiv preprint arxiv:1905.10947, 2019 - arxiv.org
Graph Neural Networks (graph NNs) are a promising deep learning approach for analyzing
graph-structured data. However, it is known that they do not improve (or sometimes worsen) …