English
Related papers

Related papers: Dynamically Stable Infinite-Width Limits of Neural…

200 papers

Graph neural networks (GNNs) achieve remarkable performance in graph machine learning tasks but can be hard to train on large-graph data, where their learning dynamics are not well understood. We investigate the training dynamics of…

Machine Learning · Computer Science 2023-06-02 Sanjukta Krishnagopal , Luana Ruiz

In training a neural network with gradient descent (GD), each iteration induces a linear operator that governs first-order updates to a model's internal state variables. We define this operator as the Global Empirical Neural Tangent Kernel…

Machine Learning · Computer Science 2026-05-12 James Hazelden , Laura Driscoll , Eli Shlizerman , Eric Shea-Brown

Expressiveness and generalization of deep models was recently addressed via the connection between neural networks (NNs) and kernel learning, where first-order dynamics of NN during a gradient-descent (GD) optimization were related to…

Machine Learning · Computer Science 2020-04-21 Dmitry Kopitkov , Vadim Indelman

While deep learning has achieved remarkable success across a wide range of applications, its theoretical understanding of representation learning remains limited. Deep neural kernels provide a principled framework to interpret…

Machine Learning · Computer Science 2025-11-11 Yong-Ming Tian , Shuang Liang , Shao-Qun Zhang , Feng-Lei Fan

In this paper, we study the data-dependent convergence and generalization behavior of gradient methods for neural networks with smooth activation. Our first result is a novel bound on the excess risk of deep networks trained by the logistic…

Machine Learning · Computer Science 2024-12-09 Hossein Taheri , Christos Thrampoulidis , Arya Mazumdar

Recent works show an intriguing phenomenon of Frequency Principle (F-Principle) that deep neural networks (DNNs) fit the target function from low to high frequency during the training, which provides insight into the training and…

Machine Learning · Computer Science 2020-10-19 Tao Luo , Zheng Ma , Zhi-Qin John Xu , Yaoyu Zhang

We study infinite limits of neural network quantum states ($\infty$-NNQS), which exhibit representation power through ensemble statistics, and also tractable gradient descent dynamics. Ensemble averages of Renyi entropies are expressed in…

Quantum Physics · Physics 2023-09-29 Di Luo , James Halverson

The prevailing thinking is that orthogonal weights are crucial to enforcing dynamical isometry and speeding up training. The increase in learning speed that results from orthogonal initialization in linear networks has been well-proven.…

Machine Learning · Computer Science 2021-07-22 Wei Huang , Weitao Du , Richard Yi Da Xu

The Neural Tangent Kernel (NTK) framework explains optimization in over-parameterized neural networks via approximately linearized dynamics, yielding exponential convergence guarantees. However, existing results are often overly pessimistic…

Machine Learning · Computer Science 2026-05-26 Ruchirinkil Marreddy , Chaoyue Liu

A recent line of work has analyzed the theoretical properties of deep neural networks via the Neural Tangent Kernel (NTK). In particular, the smallest eigenvalue of the NTK has been related to the memorization capacity, the global…

Machine Learning · Statistics 2022-08-23 Quynh Nguyen , Marco Mondelli , Guido Montufar

In this paper, we provide the first precise distributional characterization of gradient descent iterates for general multi-layer neural networks under the canonical single-index regression model, in the `finite-width proportional regime'…

Machine Learning · Computer Science 2025-05-09 Qiyang Han , Masaaki Imaizumi

We prove that a randomly initialized neural network of *any architecture* has its Tangent Kernel (NTK) converge to a deterministic limit, as the network widths tend to infinity. We demonstrate how to calculate this limit. In prior…

Machine Learning · Statistics 2020-12-01 Greg Yang

In practice, multi-task learning (through learning features shared among tasks) is an essential property of deep neural networks (NNs). While infinite-width limits of NNs can provide good intuition for their generalization behavior, the…

Machine Learning · Computer Science 2022-10-21 Jakob Heiss , Josef Teichmann , Hanna Wutte

Small generalization errors of over-parameterized neural networks (NNs) can be partially explained by the frequency biasing phenomenon, where gradient-based algorithms minimize the low-frequency misfit before reducing the high-frequency…

Machine Learning · Computer Science 2022-09-27 Annan Yu , Yunan Yang , Alex Townsend

The brain's activity is characterized by the interaction of a very large number of neurons that are strongly affected by noise. However, signals often arise at macroscopic scales integrating the effect of many neurons into a reliable…

Dynamical Systems · Mathematics 2012-11-07 Jonathan Touboul , G. Bard Ermentrout

We provide quantitative bounds measuring the $L^2$ difference in function space between the trajectory of a finite-width network trained on finitely many samples from the idealized kernel dynamics of infinite width and infinite data. An…

Machine Learning · Statistics 2022-10-18 Benjamin Bowman , Guido Montufar

Recent works have partly attributed the generalization ability of over-parameterized neural networks to frequency bias -- networks trained with gradient descent on data drawn from a uniform distribution find a low frequency fit before high…

Machine Learning · Computer Science 2020-03-11 Ronen Basri , Meirav Galun , Amnon Geifman , David Jacobs , Yoni Kasten , Shira Kritchman

Fully-connected deep neural networks with weights initialized from independent Gaussian distributions can be tuned to criticality, which prevents the exponential growth or decay of signals propagating through the network. However, such…

Machine Learning · Computer Science 2024-06-13 Hannah Day , Yonatan Kahn , Daniel A. Roberts

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

Previous influential work showed that infinite width limits of neural networks in the lazy training regime are described by kernel machines. Here, we show that neural networks trained in the rich, feature learning infinite-width regime in…

Machine Learning · Computer Science 2025-09-12 Clarissa Lauditi , Blake Bordelon , Cengiz Pehlevan