English
Related papers

Related papers: Path Integral Approach to Random Neural Networks

200 papers

The goal of this thesis is to improve our understanding of the internal mechanisms by which deep artificial neural networks create meaningful representations and are able to generalize. We focus on the challenge of characterizing the…

Machine Learning · Computer Science 2025-10-29 Diego Doimo

Growing evidence suggests that synaptic weights in the brain follow heavy-tailed distributions, yet most theoretical analyses of recurrent neural networks (RNNs) assume Gaussian connectivity. We systematically study the activity of RNNs…

Neurons and Cognition · Quantitative Biology 2025-10-27 Yi Xie , Stefan Mihalas , Łukasz Kuśmierz

We study the mean-field limit and stationary distributions of a pulse-coupled network modeling the dynamics of a large neuronal assemblies. Our model takes into account explicitly the intrinsic randomness of firing times, contrasting with…

Probability · Mathematics 2015-03-17 Philippe Robert , Jonathan D. Touboul

We establish central and non-central limit theorems for sequences of functionals of the Gaussian output of an infinitely-wide random neural network on the d-dimensional sphere . We show that the asymptotic behaviour of these functionals as…

Probability · Mathematics 2026-04-24 Simmaco Di Lillo , Leonardo Maini , Domenico Marinucci

The path integral approach offers not only an exact expression for the non- equilibrium dynamics of dissipative quantum systems, but is also a convenient starting point for perturbative treatments. An alternative way to explore the…

Statistical Mechanics · Physics 2022-09-21 Joachim Ankerhold

We analyze the macroscopic behavior of multi-populations randomly connected neural networks with interaction delays. Similar to cases occurring in spin glasses, we show that the sequences of empirical measures satisfy a large deviation…

Mathematical Physics · Physics 2015-06-15 Tanguy Cabana , Jonathan Touboul

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

Dynamical systems driven by strong external signals are ubiquituous in nature and engineering. Here we study "echo state networks", networks of a large number of randomly connected nodes, which represent a simple model of a neural network,…

Chaotic Dynamics · Physics 2013-11-07 Marc Massar , Serge Massar

We present a new path integral method to analyze stochastically perturbed ordinary differential equations with multiple time scales. The objective of this method is to derive from the original system a new stochastic differential equation…

Pattern Formation and Solitons · Physics 2007-08-20 Tobias Schaefer Richard O. Moore

The main difficulty that arises in the analysis of most machine learning algorithms is to handle, analytically and numerically, a large number of interacting random variables. In this Ph.D manuscript, we revisit an approach based on the…

Disordered Systems and Neural Networks · Physics 2021-03-11 Benjamin Aubin

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

We consider pulse-coupled Leaky Integrate-and-Fire neural networks with randomly distributed synaptic couplings. This random dilution induces fluctuations in the evolution of the macroscopic variables and deterministic chaos at the…

Chaotic Dynamics · Physics 2015-04-14 D. Angulo-Garcia , A. Torcini

The capability of recurrent neural networks to approximate trajectories of a random dynamical system, with random inputs, on non-compact domains, and over an indefinite or infinite time horizon is considered. The main result states that…

Neural and Evolutionary Computing · Computer Science 2022-11-16 Adrian N. Bishop

We review various methods to investigate the statics and the dynamics of collective composition fluctuations in dense polymer mixtures within fluctuating-field approaches. The central idea of fluctuating-field theories is to rewrite the…

Soft Condensed Matter · Physics 2007-05-23 Marcus Mueller , Friederike Schmid

Deep Neural Networks (DNNs) rely on inherent fluctuations in their internal parameters (weights and biases) to effectively navigate the complex optimization landscape and achieve robust performance. While these fluctuations are recognized…

Machine Learning · Computer Science 2025-11-14 Darsh Pareek , Umesh Kumar , Ruthu Rao , Ravi Janjam

We present an early investigation into the use of neural diffusion processes for global optimisation, focusing on Zhang et al.'s Path Integral Sampler. One can use the Boltzmann distribution to formulate optimization as solving a…

Machine Learning · Computer Science 2025-06-10 Max McGuinness , Eirik Fladmark , Francisco Vargas

A common network inference problem, arising from real-world data constraints, is how to infer a dynamic network from its time-aggregated adjacency matrix and time-varying marginals (i.e., row and column sums). Prior approaches to this…

Machine Learning · Statistics 2024-08-21 Serina Chang , Frederic Koehler , Zhaonan Qu , Jure Leskovec , Johan Ugander

In this article, we consider limit theorems for some weighted type random sums (or discrete rough integrals). We introduce a general transfer principle from limit theorems for unweighted sums to limit theorems for weighted sums via rough…

Probability · Mathematics 2017-07-07 Yanghui Liu , Samy Tindel

Time-irreversible stochastic processes are frequently used in natural sciences to explain non-equilibrium phenomena and to design efficient stochastic algorithms. Our main goal in this thesis is to analyse their dynamics by means of large…

Probability · Mathematics 2021-09-21 Mikola C. Schlottke

Many methods have been proposed to quantify the predictive uncertainty associated with the outputs of deep neural networks. Among them, ensemble methods often lead to state-of-the-art results, though they require modifications to the…

Machine Learning · Computer Science 2021-05-11 Zhiyun Lu , Eugene Ie , Fei Sha