English
Related papers

Related papers: Potentials in recurrent networks: a survey

200 papers

In this paper we discuss the stability properties of convolutional neural networks. Convolutional neural networks are widely used in machine learning. In classification they are mainly used as feature extractors. Ideally, we expect similar…

Machine Learning · Computer Science 2017-01-20 Radu Balan , Maneesh Singh , Dongmian Zou

Rademacher theorem states that every Lipschitz function on the Euclidean space is differentiable almost everywhere, where "almost everywhere" refers to the Lebesgue measure. In this paper we prove a differentiability result of similar type,…

Classical Analysis and ODEs · Mathematics 2015-03-27 Giovanni Alberti , Andrea Marchese

Viewing recurrent neural networks (RNNs) as continuous-time dynamical systems, we propose a recurrent unit that describes the hidden state's evolution with two parts: a well-understood linear component plus a Lipschitz nonlinearity. This…

Machine Learning · Computer Science 2021-04-27 N. Benjamin Erichson , Omri Azencot , Alejandro Queiruga , Liam Hodgkinson , Michael W. Mahoney

We discuss the potential scattering on the noncompact star graph. The Schr\"{o}dinger operator with the short-range potential localizing in a neighborhood of the graph vertex is considered. We study the asymptotic behavior the corresponding…

Spectral Theory · Mathematics 2015-05-19 Stepan Man'ko

The zero-error capacity of a classical channel is a parameter of its confusability graph, and is equal to the minimum of the values of graph parameters that are additive under the disjoint union, multiplicative under the strong product,…

Information Theory · Computer Science 2022-07-22 Péter Vrana

Let $\Omega\subset\mathbb R^2$ be a chord arc domain. We give a simple proof of the the following fact, which is commonly known to be true: a nontrivial harmonic function which vanishes continuously on a relatively open set of the boundary…

Analysis of PDEs · Mathematics 2026-04-20 Stefano Vita

We find a canonical decomposition of a geodesic current on a surface of finite type arising from a topological decomposition of the surface along special geodesics. We show that each component either is associated to a measured lamination…

Geometric Topology · Mathematics 2017-10-20 Marc Burger , Alessandra Iozzi , Anne Parreau , Maria Beatrice Pozzetti

This note shows that, for a fixed Lipschitz constant $L > 0$, one layer neural networks that are $L$-Lipschitz are dense in the set of all $L$-Lipschitz functions with respect to the uniform norm on bounded sets.

Machine Learning · Statistics 2020-09-30 Stephan Eckstein

We introduce a new approach to traces on the principal ideal $\mathcal L_{1,\infty}$ generated by any positive compact operator whose singular value sequence is the harmonic sequence. Distinct from the well-known construction of J.~Dixmier,…

Operator Algebras · Mathematics 2016-12-15 Evgenii Semenov , Fedor Sukochev , Aleksandr Usachev , Dmitriy Zanin

The Teichm\"uller harmonic map flow is a gradient flow for the harmonic map energy of maps from a closed surface to a general closed Riemannian target manifold of any dimension, where both the map and the domain metric are allowed to…

Differential Geometry · Mathematics 2015-10-19 Tobias Huxol , Melanie Rupflin , Peter M. Topping

In this paper, we consider the existence and multiplicity of solutions for the logarithmic Schr\"{o}dinger equation on lattice graphs $\mathbb{Z}^N$ $$ -\Delta u+V(x) u=u \log u^2, \quad x \in \mathbb{Z}^N, $$ When the potential $V$ is…

Analysis of PDEs · Mathematics 2024-03-26 Zhentao He , Chao Ji

This article studies the Gram random matrix model $G=\frac1T\Sigma^{\rm T}\Sigma$, $\Sigma=\sigma(WX)$, classically found in the analysis of random feature maps and random neural networks, where $X=[x_1,\ldots,x_T]\in{\mathbb R}^{p\times…

Probability · Mathematics 2017-06-30 Cosme Louart , Zhenyu Liao , Romain Couillet

In this paper, we study the problem of optimizing a two-layer artificial neural network that best fits a training dataset. We look at this problem in the setting where the number of parameters is greater than the number of sampled points.…

Machine Learning · Computer Science 2017-11-01 Digvijay Boob , Guanghui Lan

We rigorously show that a large family of monotone quantities along the weak inverse mean curvature flow is the limit case of the corresponding ones along the level sets of $p$-capacitary potentials. Such monotone quantities include…

Differential Geometry · Mathematics 2026-02-10 Luca Benatti , Alessandra Pluda , Marco Pozzetta

We present an analog to classic potential theory on weighted graphs. With nodes partitioned into exterior, boundary and interior nodes and an appropriate decomposition of the Laplacian, we define discrete analogues to the trace operators,…

Probability · Mathematics 2025-08-04 Trent DeGiovanni , Fernando Guevara Vasquez

We normalize the combinatorial Laplacian of a graph by the degree sum, look at its eigenvalues as a probability distribution and then study its Shannon entropy. Equivalently, we represent a graph with a quantum mechanical state and study…

Disordered Systems and Neural Networks · Physics 2012-04-24 Filippo Passerini , Simone Severini

In this note we discuss how several results characterizing the qualitative behavior of solutions to the nonlinear Poisson equation can be generalized to harmonic maps with potential between complete Riemannian manifolds. This includes…

Differential Geometry · Mathematics 2017-08-04 Volker Branding

We prove a Landis type unique continuation result for positive quasi-linear operators on graphs. Specifically, we give decay criteria that ensures when a harmonic function for a positive quasilinear Schr\"odinger operator with potential…

Analysis of PDEs · Mathematics 2025-09-26 Ujjal Das , Matthias Keller , Yehuda Pinchover

In the context of geodesic flows of noncompact negatively curved manifolds, we propose three different definitions of entropy and pressure at infinity, through growth of periodic orbits, critical exponents of Poincar\'e series, and entropy…

Differential Geometry · Mathematics 2023-03-08 Sébastien Gouëzel , Camille Noûs , Barbara Schapira , Samuel Tapie , Felipe Riquelme

In this paper, we prove some splitting results for manifolds supporting a non-constant infinity harmonic function which has at most linear growth on one side. Manifolds with non-negative Ricci or sectional curvature are considered. In…

Differential Geometry · Mathematics 2024-10-15 Damião J. Araújo , Marco Magliaro , Luciano Mari , Leandro F. Pessoa
‹ Prev 1 4 5 6 7 8 10 Next ›