English
Related papers

Related papers: Large deviations for randomly connected neural net…

200 papers

We study the asymptotics of large, moderate and normal deviations for the connected components of the sparse random graph by the method of stochastic processes. We obtain the logarithmic asymptotics of large deviations of the joint…

Probability · Mathematics 2007-05-23 Anatolii A. Puhalskii

The theory of stochastic approximations form the theoretical foundation for studying convergence properties of many popular recursive learning algorithms in statistics, machine learning and statistical physics. Large deviations for…

Probability · Mathematics 2025-02-05 Henrik Hult , Adam Lindhe , Pierre Nyquist , Guo-Jhen Wu

Let $\Delta^o$ be a finite set and, for each probability measure $m$ on $\Delta^o$, let $G(m)$ be a transition probability kernel on $\Delta^o$. Fix $x_0 \in \Delta^o$ and consider the chain $\{X_n, \; n \in \mathbb{N}_0\}$ of…

Probability · Mathematics 2025-07-15 Amarjit Budhiraja , Adam Waterbury , Pavlos Zoubouloglou

In modern deep learning, there is a recent and growing literature on the interplay between large-width asymptotic properties of deep Gaussian neural networks (NNs), i.e. deep NNs with Gaussian-distributed weights, and Gaussian stochastic…

Machine Learning · Computer Science 2022-06-27 Stefano Favaro , Sandra Fortini , Stefano Peluchetti

We propose a general framework to extract microscopic interactions from raw configurations with deep neural networks. The approach replaces the modeling Hamiltonian by the neural networks, in which the interaction is encoded. It can be…

Computational Physics · Physics 2020-08-19 Lingxiao Wang , Yin Jiang , Kai Zhou

We study two problems. First, we consider the large deviation behavior of empirical measures of certain diffusion processes as, simultaneously, the time horizon becomes large and noise becomes vanishingly small. The law of large numbers…

Probability · Mathematics 2023-09-14 Amarjit Budhiraja , Pavlos Zoubouloglou

We establish the large deviations asymptotic performance (error exponent) of consensus+innovations distributed detection over random networks with generic (non-Gaussian) sensor observations. At each time instant, sensors 1) combine theirs…

Information Theory · Computer Science 2015-06-03 Dragana Bajovic , Dusan Jakovetic , Jose M. F. Moura , Joao Xavier , Bruno Sinopoli

A distributed average consensus algorithm in which every sensor transmits with bounded peak power is proposed. In the presence of communication noise, it is shown that the nodes reach consensus asymptotically to a finite random variable…

Distributed, Parallel, and Cluster Computing · Computer Science 2015-06-15 Sivaraman Dasarathan , Cihan Tepedelenlioglu , Mahesh Banavar , Andreas Spanias

This paper considers the consensus problem for a network of nodes with random interactions and sampled-data control actions. We first show that consensus in expectation, in mean square, and almost surely are equivalent for a general random…

Systems and Control · Computer Science 2016-08-24 Junfeng Wu , Ziyang Meng , Tao Yang , Guodong Shi , Karl H. Johansson

The cortex is a very large network characterized by a complex connectivity including at least two scales: a microscopic scale at which the interconnections are non-specific and very dense, while macroscopic connectivity patterns connecting…

Neurons and Cognition · Quantitative Biology 2015-06-17 Jonathan Touboul

Many mathematical models of interacting agents assume that individual interactions scale down in proportion to the network size, ensuring that the combined input received from the network does not diverge. In theoretical neuroscience,…

Analysis of PDEs · Mathematics 2025-11-10 Cristobal Quininao , Jonathan Touboul

We continue the development, started in of the asymptotic description of certain stochastic neural networks. We use the Large Deviation Principle (LDP) and the good rate function H announced there to prove that H has a unique minimum mu_e,…

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

We study binary state dynamics on a network where each node acts in response to the average state of its neighborhood. Allowing varying amounts of stochasticity in both the network and node responses, we find different outcomes in random…

Physics and Society · Physics 2014-07-09 Kameron Decker Harris , Christopher M. Danforth , Peter Sheridan Dodds

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

Understanding the dynamics of spatially extended systems represents a challenge in diverse scientific disciplines, ranging from physics and mathematics to the earth and climate sciences or the neurosciences. This challenge has stimulated…

Data Analysis, Statistics and Probability · Physics 2012-08-06 S. Bialonski

We investigate two asymptotic properties of a spatial preferential-attachment model introduced by E. Jacob and P. M\"orters (2013). First, in a regime of strong linear reinforcement, we show that typical distances are at most of…

Probability · Mathematics 2018-09-28 Christian Hirsch , Christian Mönch

We consider the quasi-deterministic behavior of systems with a large number, $n$, of deterministically interacting constituents. This work extends the results of a previous paper [J. Stat. Phys. 99:1225-1249 (2000)] to include vector-valued…

Statistical Mechanics · Physics 2021-04-28 Brian R. La Cour , William C. Schieve

We study the large-volume asymptotics of the sum of power-weighted edge lengths $\sum_{e \in E}|e|^\alpha$ in Poisson-based spatial random networks. In the regime $\alpha > d$, we provide a set of sufficient conditions under which the upper…

Probability · Mathematics 2025-01-08 Christian Hirsch , Daniel Willhalm

A basic result of large deviations theory is Sanov's theorem, which states that the sequence of empirical measures of independent and identically distributed samples satisfies the large deviation principle with rate function given by…

Probability · Mathematics 2014-10-17 Markus Fischer

We show that under certain simple assumptions on the topology (structure) of networks of strongly interacting chaotic elements a phenomenon of long range action takes place, namely that the asymptotic (as time goes to infinity) dynamics of…

Dynamical Systems · Mathematics 2009-11-11 Michael Blank , Leonid Bunimovich