English
Related papers

Related papers: Collective evolution of weights in wide neural net…

200 papers

Complex networks serve as abstract models for understanding real-world complex systems and provide frameworks for studying structured dynamical systems. This article addresses limitations in current studies on the exploration of individual…

Social and Information Networks · Computer Science 2025-10-14 Bin Pi , Liang-Jian Deng , Minyu Feng , Matjaž Perc , Jürgen Kurths

Several problems in machine learning are naturally expressed as the design and analysis of time-evolving probability distributions. This includes sampling via diffusion methods, optimizing the weights of neural networks, and analyzing the…

Optimization and Control · Mathematics 2026-05-28 Gabriel Peyré

We consider kinetic systems and prove their stability working in weighted spaces in which the systems are symmetric. We prove stability for various explicit and implicit semi-discrete and fully discrete schemes. The applications include…

Numerical Analysis · Mathematics 2017-08-07 F. Patricia Medina , Malgorzata Peszynska

For percolating systems, we propose a universal exponent relation connecting the leading corrections to scaling of the cluster size distribution with the dynamic corrections to the asymptotic transport behaviour at criticality. Our…

Statistical Mechanics · Physics 2008-12-08 Axel Kammerer , Felix Höfling , Thomas Franosch

This paper considers the equilibrium-free stability and performance analysis of discrete-time nonlinear systems. We consider two types of equilibrium-free notions. Namely, the universal shifted concept, which considers stability and…

Systems and Control · Electrical Eng. & Systems 2024-02-16 Patrick J. W. Koelewijn , Siep Weiland , Roland Tóth

The largely successful method of training neural networks is to learn their weights using some variant of stochastic gradient descent (SGD). Here, we show that the solutions found by SGD can be further improved by ensembling a subset of the…

Predictive models that generalize well under distributional shift are often desirable and sometimes crucial to building robust and reliable machine learning applications. We focus on distributional shift that arises in causal inference from…

Machine Learning · Statistics 2018-02-27 Fredrik D. Johansson , Nathan Kallus , Uri Shalit , David Sontag

In this paper we study the problem of learning Rectified Linear Units (ReLUs) which are functions of the form $max(0,<w,x>)$ with $w$ denoting the weight vector. We study this problem in the high-dimensional regime where the number of…

Machine Learning · Computer Science 2017-08-03 Mahdi Soltanolkotabi

In this work we systematically analyze general properties of differential equations used as machine learning models. We demonstrate that the gradient of the loss function with respect to to the hidden state can be considered as a…

Machine Learning · Statistics 2019-10-30 Julius Ruseckas

We consider an evolution equation of parabolic type in R having a travelling wave solution. We perform an appropriate change of variables which transforms the equation into a non local evolution one having a travelling wave solution with…

Analysis of PDEs · Mathematics 2015-03-17 Jose M. Arrieta , Maria Lopez-Fernandez , Enrique Zuazua

We report on recent progress in the study of evolution processes involving degenerate parabolic equations what may exhibit free boundaries. The equations we have selected follow to recent trends in diffusion theory: considering anomalous…

Analysis of PDEs · Mathematics 2016-02-17 Jose Antonio Carrillo , Juan Luis Vazquez

We consider the dynamics of gradient descent (GD) in overparameterized single hidden layer neural networks with a squared loss function. Recently, it has been shown that, under some conditions, the parameter values obtained using GD achieve…

Machine Learning · Computer Science 2021-05-17 Siddhartha Satpathi , R Srikant

Using a simple model with link removals as well as link additions, we show that an evolving network is scale free with a degree exponent in the range of (2, 4]. We then establish a relation between the network evolution and a set of…

Mathematical Physics · Physics 2007-05-23 Dinghua Shi , Liming Liu , Xiang Zhu , Huijie Zhou , Binbin Wang

We present a general variational framework for the training of freeform nonlinearities in layered computational architectures subject to some slope constraints. The regularization that we add to the traditional training loss penalizes the…

Machine Learning · Statistics 2025-03-31 Michael Unser , Alexis Goujon , Stanislas Ducotterd

We show analytically that training a neural network by conditioned stochastic mutation or neuroevolution of its weights is equivalent, in the limit of small mutations, to gradient descent on the loss function in the presence of Gaussian…

Neural and Evolutionary Computing · Computer Science 2022-01-05 Stephen Whitelam , Viktor Selin , Sang-Won Park , Isaac Tamblyn

Many experiments have been performed that use evolutionary algorithms for learning the topology and connection weights of a neural network that controls a robot or virtual agent. These experiments are not only performed to better understand…

Neural and Evolutionary Computing · Computer Science 2019-05-23 Benjamin Inden , Jürgen Jost

We study a class of stochastic evolution equations with a dissipative forcing nonlinearity and additive noise. The noise is assumed to satisfy rather general assumptions about the form of the covariance function; our framework covers…

Probability · Mathematics 2009-11-23 Stefano Bonaccorsi , Ciprian Tudor

The paper introduces the weighted convolution, a novel approach to the convolution for signals defined on regular grids (e.g., 2D images) through the application of an optimal density function to scale the contribution of neighbouring…

Computer Vision and Pattern Recognition · Computer Science 2025-06-02 Simone Cammarasana , Giuseppe Patanè

We study a nonlinear recombination model from population genetics as a combinatorial version of the Kac-Boltzmann equation from kinetic theory. Following Kac's approach, the nonlinear model is approximated by a mean field linear evolution…

Probability · Mathematics 2024-12-24 Pietro Caputo , Daniel Parisi

In this work we study a simple evolutionary model of bipartite networks which its evolution is based on the duplication of nodes. Using analytical results along with numerical simulation of the model, we show that the above evolutionary…

Disordered Systems and Neural Networks · Physics 2009-11-10 A. Ramezanpour