English
Related papers

Related papers: Mean-field theory of learning: from dynamics to st…

200 papers

Using the cavity method and diagrammatic methods, we model the dynamics of batch learning of restricted sets of examples, widely applicable to general learning cost functions, and fully taking into account the temporal correlations…

Disordered Systems and Neural Networks · Physics 2009-10-31 K. Y. Michael Wong , S. Li , Y. W. Tong

Rich out of equilibrium collective dynamics of strongly interacting large assemblies emerge in many areas of science. Some intriguing and not fully understood examples are the glassy arrest in atomic, molecular or colloidal systems,…

Statistical Mechanics · Physics 2023-05-03 Leticia F. Cugliandolo

Dynamical mean-field theory is a powerful physics tool used to analyze the typical behavior of neural networks, where neurons can be recurrently connected, or multiple layers of neurons can be stacked. However, it is not easy for beginners…

Disordered Systems and Neural Networks · Physics 2024-02-21 Wenxuan Zou , Haiping Huang

The dynamical and stationary properties of on-line learning from finite training sets are analysed using the cavity method. For large input dimensions, we derive equations for the macroscopic parameters, namely, the student-teacher…

Disordered Systems and Neural Networks · Physics 2009-11-07 Peixun Luo , K. Y. Michael Wong

Dynamical Mean-Field Theory (DMFT) is a powerful theoretical framework for analyzing systems with many interacting degrees of freedom. This tutorial provides an accessible introduction to DMFT. We begin with a linear model where the DMFT…

Disordered Systems and Neural Networks · Physics 2025-07-23 Emmy Blumenthal

We analyze the learning of noisy teacher-generated examples by nonlinear and differentiable student perceptrons using the cavity method. The generic activation of an example is a function of the cavity activation of the example, which is…

Disordered Systems and Neural Networks · Physics 2009-11-07 Peixun Luo , K. Y. Michael Wong

The dynamics of minority games with agents trading on different time scales is studied via dynamical mean-field theory. We analyze the case where the agents' decision-making process is deterministic and its stochastic generalization with…

Disordered Systems and Neural Networks · Physics 2009-11-10 Andrea De Martino

We discuss here the mean-field theory for a cellular automata model of meta-learning. The meta-learning is the process of combining outcomes of individual learning procedures in order to determine the final decision with higher accuracy…

Machine Learning · Statistics 2015-05-13 Dariusz Plewczynski

Using the cavity method we consider the learning of noisy teacher-generated examples by a nonlinear student perceptron. For insufficient examples and weak weight decay, the activation distribution of the training examples exhibits a gap for…

Disordered Systems and Neural Networks · Physics 2007-05-23 Peixun Luo , K. Y. Michael Wong

Mean-field theory is a powerful tool for studying large neural networks. However, when the system is composed of a few neurons, macroscopic differences between the mean-field approximation and the real behavior of the network can arise.…

Neurons and Cognition · Quantitative Biology 2016-09-28 Diego Fasoli , Anna Cattani , Stefano Panzeri

Although real-world complex systems typically interact through sparse and heterogeneous networks, analytic solutions of their dynamics are limited to models with all-to-all interactions. Here, we solve the dynamics of a broad range of…

Disordered Systems and Neural Networks · Physics 2025-01-28 Fernando L. Metz

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 study inference and reconstruction of couplings in a partially observed kinetic Ising model. With hidden spins, calculating the likelihood of a sequence of observed spin configurations requires performing a trace over the configurations…

Disordered Systems and Neural Networks · Physics 2021-04-13 Benjamin Dunn , Yasser Roudi

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

In this paper, we examine the convergence landscape of multi-agent learning under uncertainty. Specifically, we analyze two stochastic models of regularized learning in continuous games -- one in continuous and one in discrete time with the…

Computer Science and Game Theory · Computer Science 2025-12-10 Kyriakos Lotidis , Panayotis Mertikopoulos , Nicholas Bambos , Jose Blanchet

The driven transport of plastic systems in various disordered backgrounds is studied within mean field theory. Plasticity is modeled using non-convex interparticle potentials that allow for phase slips. This theory most naturally describes…

Disordered Systems and Neural Networks · Physics 2009-11-10 Karl Saunders , J. M. Schwarz , M. Cristina Marchetti , A. Alan Middleton

A dynamical model of an ecological community is analyzed within a "mean-field approximation" in which one of the species interacts with the combination of all of the other species in the community. Within this approximation the model may be…

Adaptation and Self-Organizing Systems · Physics 2009-10-31 Alan McKane , David Alonso , Ricard V. Sole

We study the dynamics of supervised learning in layered neural networks, in the regime where the size $p$ of the training set is proportional to the number $N$ of inputs. Here the local fields are no longer described by Gaussian probability…

Disordered Systems and Neural Networks · Physics 2009-10-31 A. C. C. Coolen , D. Saad

The ability to learn from a small number of examples has been a difficult problem in machine learning since its inception. While methods have succeeded with large amounts of training data, research has been underway in how to accomplish…

Machine Learning · Computer Science 2017-08-24 Nathan Hilliard , Nathan O. Hodas , Courtney D. Corley

A dynamic mean field theory is developed for finite state and action Bayesian reinforcement learning in the large state space limit. In an analogy with statistical physics, the Bellman equation is studied as a disordered dynamical system;…

Machine Learning · Statistics 2023-07-13 George Stamatescu
‹ Prev 1 2 3 10 Next ›