English
Related papers

Related papers: Random Fully Connected Neural Networks as Perturba…

200 papers

We study the expressivity of one-dimensional (1D) ReLU deep neural networks through the lens of their linear regions. For randomly initialized, fully connected 1D ReLU networks (He scaling with nonzero bias) in the infinite-width limit, we…

Machine Learning · Computer Science 2025-12-10 Jonathan Kogan , Hayden Jananthan , Jeremy Kepner

In this paper, we consider regression problems with one-hidden-layer neural networks (1NNs). We distill some properties of activation functions that lead to $\mathit{local~strong~convexity}$ in the neighborhood of the ground-truth…

Machine Learning · Computer Science 2017-06-13 Kai Zhong , Zhao Song , Prateek Jain , Peter L. Bartlett , Inderjit S. Dhillon

Deep Neural Networks and Reinforcement Learning methods have empirically shown great promise in tackling challenging combinatorial problems. In those methods a deep neural network is used as a solution generator which is then trained by…

Machine Learning · Computer Science 2023-11-08 Constantine Caramanis , Dimitris Fotakis , Alkis Kalavasis , Vasilis Kontonis , Christos Tzamos

In the context of classification problems, Deep Learning (DL) approaches represent state of art. Many DL approaches are based on variations of standard multi-layer feed-forward neural networks. These are also referred to as deep networks.…

Machine Learning · Computer Science 2023-11-21 Andrea Apicella , Francesco Isgrò , Roberto Prevete

We study deep neural networks with polynomial activations, particularly their expressive power. For a fixed architecture and activation degree, a polynomial neural network defines an algebraic map from weights to polynomials. The image of…

Machine Learning · Computer Science 2019-05-30 Joe Kileel , Matthew Trager , Joan Bruna

We investigate the computational complexity of various problems for simple recurrent neural networks (RNNs) as formal models for recognizing weighted languages. We focus on the single-layer, ReLU-activation, rational-weight RNNs with…

Formal Languages and Automata Theory · Computer Science 2018-03-06 Yining Chen , Sorcha Gilroy , Andreas Maletti , Jonathan May , Kevin Knight

Deep networks are powerful function approximators, but they typically store many different computations in shared weight matrices, making it difficult to selectively reuse or adapt parts of them when a familiar structure appears in novel…

Machine Learning · Computer Science 2026-05-28 Niclas Pokel , Benjamin F. Grewe

A robust theoretical framework that can describe and predict the generalization ability of deep neural networks (DNNs) in general circumstances remains elusive. Classical attempts have produced complexity metrics that rely heavily on global…

Machine Learning · Computer Science 2020-01-20 Marelie H. Davel , Marthinus W. Theunissen , Arnold M. Pretorius , Etienne Barnard

While deep learning is successful in a number of applications, it is not yet well understood theoretically. A satisfactory theoretical characterization of deep learning however, is beginning to emerge. It covers the following questions: 1)…

Machine Learning · Computer Science 2019-08-27 Tomaso Poggio , Andrzej Banburski , Qianli Liao

Polynomial Neural Networks (PNNs) possess a rich algebraic and geometric structure. However, their identifiability -- a key property for ensuring interpretability -- remains poorly understood. In this work, we present a comprehensive…

Machine Learning · Computer Science 2026-02-03 Konstantin Usevich , Ricardo Borsoi , Clara Dérand , Marianne Clausel

In this paper we consider the limiting case of neural networks (NNs) architectures when the number of neurons in each hidden layer and the number of hidden layers tend to infinity thus forming a continuum, and we derive approximation errors…

Machine Learning · Computer Science 2026-05-12 Christophe Prieur , Mircea Lazar , Bogdan Robu

Deep neural networks based on linear RNNs interleaved with position-wise MLPs are gaining traction as competitive approaches for sequence modeling. Examples of such architectures include state-space models (SSMs) like S4, LRU, and Mamba:…

Machine Learning · Computer Science 2024-06-06 Antonio Orvieto , Soham De , Caglar Gulcehre , Razvan Pascanu , Samuel L. Smith

Convolutional Neural Networks (CNNs) have recently led to incredible breakthroughs on a variety of pattern recognition problems. Banks of finite impulse response filters are learned on a hierarchy of layers, each contributing more abstract…

Computer Vision and Pattern Recognition · Computer Science 2017-07-18 Felipe Petroski Such , Shagan Sah , Miguel Dominguez , Suhas Pillai , Chao Zhang , Andrew Michael , Nathan Cahill , Raymond Ptucha

Universality results for equivariant neural networks remain rare. Those that do exist typically hold only in restrictive settings: either they rely on regular or higher-order tensor representations, leading to impractically high-dimensional…

Machine Learning · Statistics 2025-10-20 Marco Pacini , Mircea Petrache , Bruno Lepri , Shubhendu Trivedi , Robin Walters

Despite the recent success of graph neural networks (GNN), common architectures often exhibit significant limitations, including sensitivity to oversmoothing, long-range dependencies, and spurious edges, e.g., as can occur as a result of…

Machine Learning · Computer Science 2021-12-06 Yongyi Yang , Tang Liu , Yangkun Wang , Jinjing Zhou , Quan Gan , Zhewei Wei , Zheng Zhang , Zengfeng Huang , David Wipf

We describe a novel family of models of multi- layer feedforward neural networks in which the activation functions are encoded via penalties in the training problem. Our approach is based on representing a non-decreasing activation function…

Machine Learning · Computer Science 2018-06-22 Armin Askari , Geoffrey Negiar , Rajiv Sambharya , Laurent El Ghaoui

To confirm that the expressive power of ReLU neural networks grows with their depth, the function $F_n = \max \{0,x_1,\ldots,x_n\}$ has been considered in the literature. A conjecture by Hertrich, Basu, Di Summa, and Skutella [NeurIPS 2021]…

Machine Learning · Computer Science 2025-02-18 Gennadiy Averkov , Christopher Hojny , Maximilian Merkert

Recursive Neural Networks (RvNNs), which compose sequences according to their underlying hierarchical syntactic structure, have performed well in several natural language processing tasks compared to similar models without structural…

Computation and Language · Computer Science 2021-06-14 Jishnu Ray Chowdhury , Cornelia Caragea

Wide neural networks with linear output layer have been shown to be near-linear, and to have near-constant neural tangent kernel (NTK), in a region containing the optimization path of gradient descent. These findings seem counter-intuitive…

Machine Learning · Computer Science 2022-03-11 Chaoyue Liu , Libin Zhu , Mikhail Belkin

We analyze recurrent neural networks with diagonal hidden-to-hidden weight matrices, trained with gradient descent in the supervised learning setting, and prove that gradient descent can achieve optimality \emph{without} massive…

Machine Learning · Computer Science 2024-10-11 Semih Cayci , Atilla Eryilmaz