English
Related papers

Related papers: Infinite Limits of Multi-head Transformer Dynamics

200 papers

To theoretically understand the behavior of trained deep neural networks, it is necessary to study the dynamics induced by gradient methods from a random initialization. However, the nonlinear and compositional structure of these models…

Machine Learning · Computer Science 2021-12-21 Karl Hajjar , Lénaïc Chizat , Christophe Giraud

Recent research has been focused on two different approaches to studying neural networks training in the limit of infinite width (1) a mean-field (MF) and (2) a constant neural tangent kernel (NTK) approximations. These two approaches have…

Machine Learning · Computer Science 2020-10-23 Eugene A. Golikov

To understand the training dynamics of neural networks (NNs), prior studies have considered the infinite-width mean-field (MF) limit of two-layer NN, establishing theoretical guarantees of its convergence under gradient flow training as…

Machine Learning · Computer Science 2022-10-31 Zhengdao Chen , Eric Vanden-Eijnden , Joan Bruna

As its width tends to infinity, a deep neural network's behavior under gradient descent can become simplified and predictable (e.g. given by the Neural Tangent Kernel (NTK)), if it is parametrized appropriately (e.g. the NTK…

Machine Learning · Computer Science 2022-07-18 Greg Yang , Edward J. Hu

The cost of hyperparameter tuning in deep learning has been rising with model sizes, prompting practitioners to find new tuning methods using a proxy of smaller networks. One such proposal uses $\mu$P parameterized networks, where the…

Machine Learning · Statistics 2023-12-11 Blake Bordelon , Lorenzo Noci , Mufan Bill Li , Boris Hanin , Cengiz Pehlevan

We study the high-dimensional training dynamics of a shallow neural network with quadratic activation in a teacher-student setup. We focus on the extensive-width regime, where the teacher and student network widths scale proportionally with…

Optimization and Control · Mathematics 2026-01-16 Simon Martin , Giulio Biroli , Francis Bach

Transformers serve as the foundational architecture for many successful large-scale models, demonstrating the ability to overfit the training data while maintaining strong generalization on unseen data, a phenomenon known as benign…

Machine Learning · Computer Science 2025-02-19 Yingying Zhang , Zhenyu Wu , Jian Li , Yong Liu

Despite recent efforts, neural networks still struggle to learn in non-stationary environments, and our understanding of catastrophic forgetting (CF) is far from complete. In this work, we perform a systematic study on the impact of model…

Machine Learning · Computer Science 2025-08-14 Jacopo Graldi , Alessandro Breccia , Giulia Lanzillotta , Thomas Hofmann , Lorenzo Noci

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

We study the effect of width on the dynamics of feature-learning neural networks across a variety of architectures and datasets. Early in training, wide neural networks trained on online data have not only identical loss curves but also…

Machine Learning · Computer Science 2023-12-07 Nikhil Vyas , Alexander Atanasov , Blake Bordelon , Depen Morwani , Sabarish Sainathan , Cengiz Pehlevan

The mean field (MF) theory of multilayer neural networks centers around a particular infinite-width scaling, where the learning dynamics is closely tracked by the MF limit. A random fluctuation around this infinite-width limit is expected…

Machine Learning · Computer Science 2021-11-01 Huy Tuan Pham , Phan-Minh Nguyen

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

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

The training and generalization dynamics of the Transformer's core mechanism, namely the Attention mechanism, remain under-explored. Besides, existing analyses primarily focus on single-head attention. Inspired by the demonstrated benefits…

Machine Learning · Computer Science 2024-10-15 Puneesh Deora , Rouzbeh Ghaderi , Hossein Taheri , Christos Thrampoulidis

We provide an overview of high dimensional dynamical systems driven by random matrices, focusing on applications to simple models of learning and generalization in machine learning theory. Using both cavity method arguments and path…

Disordered Systems and Neural Networks · Physics 2026-01-12 Blake Bordelon , Cengiz Pehlevan

We consider dynamical and geometrical aspects of deep learning. For many standard choices of layer maps we display semi-invariant metrics which quantify differences between data or decision functions. This allows us, when considering random…

Machine Learning · Computer Science 2021-04-23 Benny Avelin , Anders Karlsson

Understanding the inductive bias and generalization properties of large overparametrized machine learning models requires to characterize the dynamics of the training algorithm. We study the learning dynamics of large two-layer neural…

Machine Learning · Statistics 2025-10-30 Andrea Montanari , Pierfrancesco Urbani

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

We analyze the dynamics of finite width effects in wide but finite feature learning neural networks. Starting from a dynamical mean field theory description of infinite width deep neural network kernel and prediction dynamics, we provide a…

Machine Learning · Statistics 2023-11-08 Blake Bordelon , Cengiz Pehlevan

The magnitude of parameter updates are considered a key factor in continual learning. However, most existing studies focus on designing diverse update strategies, while a theoretical understanding of the underlying mechanisms remains…

Machine Learning · Computer Science 2026-02-25 JinLi He , Liang Bai , Xian Yang
‹ Prev 1 2 3 10 Next ›