English
Related papers

Related papers: Asymptotic properties of one-layer artificial neur…

200 papers

Machine learning, and in particular neural network models, have revolutionized fields such as image, text, and speech recognition. Today, many important real-world applications in these areas are driven by neural networks. There are also…

Probability · Mathematics 2019-11-12 Justin Sirignano , Konstantinos Spiliopoulos

Through the success of deep learning in various domains, artificial neural networks are currently among the most used artificial intelligence methods. Taking inspiration from the network properties of biological neural networks (e.g.…

Neural and Evolutionary Computing · Computer Science 2018-06-21 Decebal Constantin Mocanu , Elena Mocanu , Peter Stone , Phuong H. Nguyen , Madeleine Gibescu , Antonio Liotta

We present a framework to define a large class of neural networks for which, by construction, training by gradient flow provably reaches arbitrarily low loss when the number of parameters grows. Distinct from the fixed-space global…

Optimization and Control · Mathematics 2025-01-13 David A. R. Robin , Kevin Scaman , Marc Lelarge

We study the asymptotic law of a network of interacting neurons when the number of neurons becomes infinite. The dynamics of the neurons is described by a set of stochastic differential equations in discrete time. The neurons interact…

Probability · Mathematics 2014-07-10 Olivier Faugeras , James MacLaurin

Coded recurrent neural networks with three levels of sparsity are introduced. The first level is related to the size of messages, much smaller than the number of available neurons. The second one is provided by a particular coding rule,…

Machine Learning · Computer Science 2011-02-22 Vincent Gripon , Claude Berrou

We introduce a model for neural scaling laws under sparse activations. In the model, test loss is often dominated by rare coordinates that are never observed in the training input. This mechanism induces a novel bottleneck absent from dense…

Machine Learning · Statistics 2026-05-25 John Sous , Michael Winer

We study large deviations in the context of stochastic gradient descent for one-hidden-layer neural networks with quadratic loss. We derive a quenched large deviation principle, where we condition on an initial weight measure, and an…

Probability · Mathematics 2025-01-14 Christian Hirsch , Daniel Willhalm

Consider a bipartite network where $N$ consumers choose to buy or not to buy $M$ different products. This paper considers the properties of the logistic regression of the $N\times M$ array of i-buys-j purchase decisions,…

Econometrics · Economics 2020-10-12 Bryan S. Graham

Sparse connectivity is a hallmark of the brain and a desired property of artificial neural networks. It promotes energy efficiency, simplifies training, and enhances the robustness of network function. Thus, a detailed understanding of how…

Disordered Systems and Neural Networks · Physics 2024-09-10 Mirza M. Junaid Baig , Armen Stepanyants

Artificial neural networks can be represented by paths. Generated as random walks on a dense network graph, we find that the resulting sparse networks allow for deterministic initialization and even weights with fixed sign. Such networks…

Machine Learning · Computer Science 2023-11-28 Alexander Keller , Matthijs Van keirsbilck

Many growing networks possess accelerating statistics where the number of links added with each new node is an increasing function of network size so the total number of links increases faster than linearly with network size. In particular,…

Molecular Networks · Quantitative Biology 2017-12-22 M. J. Gagen , J. S. Mattick

Random network models generated using sparse exchangeable graphs have provided a mechanism to study a wide variety of complex real-life networks. In particular, these models help with investigating power-law properties of degree…

Statistics Theory · Mathematics 2021-06-17 Bikramjit Das , Tiandong Wang , Gengling Dai

We study the asymptotic law of a network of interacting neurons when the number of neurons becomes infinite. Given a completely connected network of neurons in which the synaptic weights are Gaussian correlated random variables, we describe…

Probability · Mathematics 2013-12-16 Olivier Faugeras , James MacLaurin

In this manuscript, we investigate the problem of how two-layer neural networks learn features from data, and improve over the kernel regime, after being trained with a single gradient descent step. Leveraging the insight from (Ba et al.,…

Machine Learning · Statistics 2024-09-06 Hugo Cui , Luca Pesce , Yatin Dandi , Florent Krzakala , Yue M. Lu , Lenka Zdeborová , Bruno Loureiro

In a series of two papers, we investigate the large deviations and asymptotic behavior of stochastic models of brain neural networks with random interaction coefficients. In this first paper, we take into account the spatial structure of…

Probability · Mathematics 2017-01-05 Tanguy Cabana , Jonathan Touboul

Improvements in the performance of deep neural networks have often come through the design of larger and more complex networks. As a result, fast memory is a significant limiting factor in our ability to improve network performance. One…

Machine Learning · Computer Science 2019-12-25 Simon Alford , Ryan Robinett , Lauren Milechin , Jeremy Kepner

The asymptotic behavior of stochastic gradient algorithms is studied. Relying on results from differential geometry (Lojasiewicz gradient inequality), the single limit-point convergence of the algorithm iterates is demonstrated and…

Optimization and Control · Mathematics 2013-09-19 Vladislav B. Tadic

Sparse Neural Networks regained attention due to their potential for mathematical and computational advantages. We give motivation to study Artificial Neural Networks (ANNs) from a network science perspective, provide a technique to embed…

Neural and Evolutionary Computing · Computer Science 2021-12-15 Julian Stier , Michael Granitzer

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

The asymptotic behavior of the stochastic gradient algorithm with a biased gradient estimator is analyzed. Relying on arguments based on the dynamic system theory (chain-recurrence) and the differential geometry (Yomdin theorem and…

Statistics Theory · Mathematics 2017-09-04 Vladislav B. Tadic , Arnaud Doucet
‹ Prev 1 2 3 10 Next ›