English
Related papers

Related papers: A Dynamical Central Limit Theorem for Shallow Neur…

200 papers

Gradient dynamics play a central role in determining the stability and generalization of deep neural networks. In this work, we provide an empirical analysis of how variance and standard deviation of gradients evolve during training,…

Machine Learning · Computer Science 2025-09-09 Vincent-Daniel Yun

Neural collapse (NC) is a phenomenon that emerges at the terminal phase of the training (TPT) of deep neural networks (DNNs). The features of the data in the same class collapse to their respective sample means and the sample means exhibit…

Machine Learning · Statistics 2024-09-09 Wanli Hong , Shuyang Ling

What scaling limits govern neural network training dynamics when model size and training time grow in tandem? We show that despite the complex interactions between architecture, training algorithms, and data, compute-optimally trained…

Machine Learning · Computer Science 2025-07-08 Shikai Qiu , Lechao Xiao , Andrew Gordon Wilson , Jeffrey Pennington , Atish Agarwala

We study the generalization of two-layer ReLU neural networks in a univariate nonparametric regression problem with noisy labels. This is a problem where kernels (\emph{e.g.} NTK) are provably sub-optimal and benign overfitting does not…

Machine Learning · Computer Science 2024-06-12 Dan Qiao , Kaiqi Zhang , Esha Singh , Daniel Soudry , Yu-Xiang Wang

In [Kozma-Toth, Ann. Probab. v 45, pp 4307-4347 (2017)] the weak CLT was established for random walks in doubly stochastic (or, divergence-free) random environments, under the following conditions: 1. Strict ellipticity assumed for the…

Probability · Mathematics 2025-01-03 Bálint Tóth

In the mean field regime, neural networks are appropriately scaled so that as the width tends to infinity, the learning dynamics tends to a nonlinear and nontrivial dynamical limit, known as the mean field limit. This lends a way to study…

Machine Learning · Computer Science 2021-05-12 Huy Tuan Pham , Phan-Minh Nguyen

Many modern neural network architectures are trained in an overparameterized regime where the parameters of the model exceed the size of the training dataset. Sufficiently overparameterized neural network architectures in principle have the…

Machine Learning · Computer Science 2019-02-14 Samet Oymak , Mahdi Soltanolkotabi

Stochastic Gradient Descent (SGD) has become a cornerstone method in modern data science. However, deploying SGD in high-stakes applications necessitates rigorous quantification of its inherent uncertainty. In this work, we establish…

Machine Learning · Computer Science 2025-10-23 Bhavya Agrawalla , Krishnakumar Balasubramanian , Promit Ghosal

We establish convergence of the training dynamics of residual neural networks (ResNets) to their joint infinite depth L, hidden width M, and embedding dimension D limit. Specifically, we consider ResNets with two-layer perceptron blocks in…

Machine Learning · Statistics 2026-03-23 Louis-Pierre Chaintron , Lénaïc Chizat , Javier Maass

We consider learning two layer neural networks using stochastic gradient descent. The mean-field description of this learning dynamics approximates the evolution of the network weights by an evolution in the space of probability…

Machine Learning · Statistics 2019-02-19 Song Mei , Theodor Misiakiewicz , Andrea Montanari

In recent years, the mean field theory has been applied to the study of neural networks and has achieved a great deal of success. The theory has been applied to various neural network structures, including CNNs, RNNs, Residual networks, and…

Machine Learning · Computer Science 2020-06-11 Wei Huang , Richard Yi Da Xu , Weitao Du , Yutian Zeng , Yunce Zhao

Deep convolutional neural networks are known to be unstable during training at high learning rate unless normalization techniques are employed. Normalizing weights or activations allows the use of higher learning rates, resulting in faster…

Machine Learning · Computer Science 2019-12-02 Brendan Ruff , Taylor Beck , Joscha Bach

Linear-threshold networks (LTNs) capture the mesoscale behavior of interacting populations of neurons and are of particular interest to control theorists due to their dynamical richness and relative ease of analysis. The aim of this paper…

Systems and Control · Electrical Eng. & Systems 2026-04-21 William Retnaraj , Simone Betteti , Alexander Davydov , Francesco Bullo , Jorge Cortes

Scaling limits, such as infinite-width limits, serve as promising theoretical tools to study large-scale models. However, it is widely believed that existing infinite-width theory does not faithfully explain the behavior of practical…

Machine Learning · Computer Science 2025-10-28 Moritz Haas , Sebastian Bordt , Ulrike von Luxburg , Leena Chennuru Vankadara

This paper studies the infinite-width limit of deep linear neural networks initialized with random parameters. We obtain that, when the number of neurons diverges, the training dynamics converge (in a precise sense) to the dynamics obtained…

Machine Learning · Computer Science 2022-12-01 Lénaïc Chizat , Maria Colombo , Xavier Fernández-Real , Alessio Figalli

Deep learning models, such as wide neural networks, can be conceptualized as nonlinear dynamical physical systems characterized by a multitude of interacting degrees of freedom. Such systems in the infinite limit, tend to exhibit simplified…

Machine Learning · Computer Science 2024-01-09 Ori Shem-Ur , Yaron Oz

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

Neural network models in neuroscience allow one to study how the connections between neurons shape the activity of neural circuits in the brain. In this chapter, we study Combinatorial Threshold-Linear Networks (CTLNs) in order to…

Neurons and Cognition · Quantitative Biology 2018-04-05 Katherine Morrison , Carina Curto

We prove error bounds in a central limit theorem for solutions of certain convolution equations. The main motivation for investigating these equations stems from applications to lace expansions, in particular to weakly self-avoiding random…

Probability · Mathematics 2014-04-11 Luca Avena , Erwin Bolthausen , Christine Ritzmann

The global clustering coefficient serves as a powerful metric for the structural analysis and comparison of complex networks. Random geometric graphs offer a realistic framework for representing the spatial constraints and geometry often…

Statistics Theory · Mathematics 2026-02-23 Mingao Yuan , Md. Niamul Islam Sium