English
Related papers

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

200 papers

We obtain the law of large numbers (LLN) and the central limit theorem (CLT) for weakly dependent non-stationary arrays of random fields with asymptotically unbounded moments. The weak dependence condition for arrays of random fields is…

Statistics Theory · Mathematics 2024-08-15 Yue Pan , Jiazhu Pan

In this paper, we rigorously derive Central Limit Theorems (CLT) for Bayesian two-layerneural networks in the infinite-width limit and trained by variational inference on a regression task. The different networks are trained via different…

Machine Learning · Statistics 2024-06-14 Arnaud Descours , Tom Huix , Arnaud Guillin , Manon Michel , Éric Moulines , Boris Nectoux

We rigorously prove a central limit theorem for neural network models with a single hidden layer. The central limit theorem is proven in the asymptotic regime of simultaneously (A) large numbers of hidden units and (B) large numbers of…

Probability · Mathematics 2019-06-04 Justin Sirignano , Konstantinos Spiliopoulos

Stochastic gradient descent in continuous time (SGDCT) provides a computationally efficient method for the statistical learning of continuous-time models, which are widely used in science, engineering, and finance. The SGDCT algorithm…

Probability · Mathematics 2019-06-18 Justin Sirignano , Konstantinos Spiliopoulos

In this paper, we characterize the noise of stochastic gradients and analyze the noise-induced dynamics during training deep neural networks by gradient-based optimizers. Specifically, we firstly show that the stochastic gradient noise…

Machine Learning · Computer Science 2021-09-22 Yixin Wu , Rui Luo , Chen Zhang , Jun Wang , Yaodong Yang

The Central Limit Theorem (CLT) establishes that sufficiently large sequences of independent and identically distributed random variables converge in probability to a normal distribution. This makes the CLT a fundamental building block of…

Logic in Computer Science · Computer Science 2026-03-10 Henning Basold , Oisín Flynn-Connolly , Chase Ford , Hao Wang

The question of whether the central limit theorem (CLT) holds for the total number of edges in exponential random graph models (ERGMs) in the subcritical region of parameters has remained an open problem. In this paper, we establish the…

Probability · Mathematics 2025-04-09 Xiao Fang , Song-Hao Liu , Qi-Man Shao , Yi-Kun Zhao

In this work, we consider a wide two-layer neural network and study the behavior of its empirical weights under a dynamics set by a stochastic gradient descent along the quadratic loss with mini-batches and noise. Our goal is to prove a…

Probability · Mathematics 2023-03-02 Arnaud Descours , Arnaud Guillin , Manon Michel , Boris Nectoux

Stochastic gradient descent (SGD) has emerged as the quintessential method in a data scientist's toolbox. Using SGD for high-stakes applications requires, however, careful quantification of the associated uncertainty. Towards that end, in…

Statistics Theory · Mathematics 2025-10-24 Bhavya Agrawalla , Krishnakumar Balasubramanian , Promit Ghosal

Linear structural error-in-variables models with univariate observations are revisited for studying modified least squares estimators of the slope and intercept. New marginal central limit theorems (CLT's) are established for these…

Statistics Theory · Mathematics 2009-09-29 Yuliya V. Martsynyuk

We analyze multi-layer neural networks in the asymptotic regime of simultaneously (A) large network sizes and (B) large numbers of stochastic gradient descent training iterations. We rigorously establish the limiting behavior of the…

Probability · Mathematics 2021-04-06 Justin Sirignano , Konstantinos Spiliopoulos

Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their scalability raises a critical question: Have we reached the scaling ceiling? This paper addresses this pivotal question by developing a unified theoretical…

Machine Learning · Computer Science 2024-12-24 Charles Luo

We consider shallow (single hidden layer) neural networks and characterize their performance when trained with stochastic gradient descent as the number of hidden units $N$ and gradient descent steps grow to infinity. In particular, we…

Machine Learning · Statistics 2022-06-02 Jiahui Yu , Konstantinos Spiliopoulos

The Central Limit Theorem (CLT) is one of the most fundamental results in statistics. It states that the standardized sample mean of a sequence of $n$ mutually independent and identically distributed random variables with finite first and…

We study the distribution of a fully connected neural network with random Gaussian weights and biases in which the hidden layer widths are proportional to a large constant $n$. Under mild assumptions on the non-linearity, we obtain…

Machine Learning · Computer Science 2024-06-18 Stefano Favaro , Boris Hanin , Domenico Marinucci , Ivan Nourdin , Giovanni Peccati

Current theoretical results on optimization trajectories of neural networks trained by gradient descent typically have the form of rigorous but potentially loose bounds on the loss values. In the present work we take a different approach…

Machine Learning · Computer Science 2021-05-04 Maksim Velikanov , Dmitry Yarotsky

We study the asymptotic shape of the trajectory of the stochastic gradient descent algorithm applied to a convex objective function. Under mild regularity assumptions, we prove a functional central limit theorem for the properly rescaled…

Machine Learning · Statistics 2026-02-18 Kessang Flamand , Victor-Emmanuel Brunel

We analyze the fluctuations of incomplete $U$-statistics over a triangular array of independent random variables. We give criteria for a Central Limit Theorem (CLT, for short) to hold in the sense that we prove that an appropriately scaled…

Probability · Mathematics 2020-03-24 Matthias Löwe , Sara Terveer

This paper develops asymptotic theory for quantile estimation via stochastic gradient descent (SGD) with a constant learning rate. The quantile loss function is neither smooth nor strongly convex. Beyond conventional perspectives and…

Machine Learning · Statistics 2026-04-06 Ziyang Wei , Jiaqi Li , Likai Chen , Wei Biao Wu

Under the high-dimensional setting that data dimension and sample size tend to infinity proportionally, we derive the central limit theorem (CLT) for linear spectral statistics (LSS) of large-dimensional sample covariance matrix. Different…

Statistics Theory · Mathematics 2021-06-21 Liu Zhijun , Bai Zhidong , Hu Jiang , Song Haiyan
‹ Prev 1 2 3 10 Next ›