English
Related papers

Related papers: Infinite-width limit of deep linear neural network…

200 papers

Deep neural networks' remarkable ability to correctly fit training data when optimized by gradient-based algorithms is yet to be fully understood. Recent theoretical results explain the convergence for ReLU networks that are wider than…

Machine Learning · Computer Science 2021-02-09 Asaf Noy , Yi Xu , Yonathan Aflalo , Lihi Zelnik-Manor , Rong Jin

Wide neural networks have proven to be a rich class of architectures for both theory and practice. Motivated by the observation that finite width convolutional networks appear to outperform infinite width networks, we study scaling laws for…

Machine Learning · Computer Science 2020-08-21 Anders Andreassen , Ethan Dyer

Deep neural networks (DNNs) at convergence consistently represent the training data in the last layer via a highly symmetric geometric structure referred to as neural collapse. This empirical evidence has spurred a line of theoretical…

Machine Learning · Computer Science 2024-10-08 Arthur Jacot , Peter Súkeník , Zihan Wang , Marco Mondelli

We consider fully connected and feedforward deep neural networks with dependent and possibly heavy-tailed weights, as introduced in [26], to address limitations of the standard Gaussian prior. It has been proved in [26] that, as the number…

Machine Learning · Statistics 2026-05-14 Nicola Apollonio , Giovanni Franzina , Giovanni Luca Torrisi

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

We analyze Elman-type Recurrent Reural Networks (RNNs) and their training in the mean-field regime. Specifically, we show convergence of gradient descent training dynamics of the RNN to the corresponding mean-field formulation in the large…

Machine Learning · Statistics 2023-03-14 Andrea Agazzi , Jianfeng Lu , Sayan Mukherjee

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

When the parameters are independently and identically distributed (initialized) neural networks exhibit undesirable properties that emerge as the number of layers increases, e.g. a vanishing dependency on the input and a concentration on…

Machine Learning · Statistics 2020-03-03 Stefano Peluchetti , Stefano Favaro

The tremendous recent progress in analyzing the training dynamics of overparameterized neural networks has primarily focused on wide networks and therefore does not sufficiently address the role of depth in deep learning. In this work, we…

Machine Learning · Computer Science 2022-06-29 Jongmin Lee , Joo Young Choi , Ernest K. Ryu , Albert No

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 results of training a neural network are heavily dependent on the architecture chosen; and even a modification of only its size, however small, typically involves restarting the training process. In contrast to this, we begin training…

Machine Learning · Computer Science 2024-02-12 Rupert Mitchell , Robin Menzenbach , Kristian Kersting , Martin Mundt

Important insights towards the explainability of neural networks reside in the characteristics of their decision boundaries. In this work, we borrow tools from the field of adversarial robustness, and propose a new perspective that relates…

Machine Learning · Computer Science 2020-10-16 Guillermo Ortiz-Jimenez , Apostolos Modas , Seyed-Mohsen Moosavi-Dezfooli , Pascal Frossard

In this paper, we show that although the minimizers of cross-entropy and related classification losses are off at infinity, network weights learned by gradient flow converge in direction, with an immediate corollary that network…

Machine Learning · Computer Science 2020-10-27 Ziwei Ji , Matus Telgarsky

In modern theoretical analyses of neural networks, the infinite-width limit is often invoked to justify Gaussian approximations of neuron preactivations (e.g., via neural network Gaussian processes or Tensor Programs). However, these…

Machine Learning · Computer Science 2026-01-05 Mana Sakai , Ryo Karakida , Masaaki Imaizumi

The population loss of trained deep neural networks often follows precise power-law scaling relations with either the size of the training dataset or the number of parameters in the network. We propose a theory that explains the origins of…

Machine Learning · Computer Science 2024-06-28 Yasaman Bahri , Ethan Dyer , Jared Kaplan , Jaehoon Lee , Utkarsh Sharma

In this paper, we study the quantitative convergence of shallow neural networks trained via gradient descent to their associated Gaussian processes in the infinite-width limit. While previous work has established qualitative convergence…

Machine Learning · Statistics 2026-03-06 Eloy Mosig , Andrea Agazzi , Dario Trevisan

We consider the idealized setting of gradient flow on the population risk for infinitely wide two-layer ReLU neural networks (without bias), and study the effect of symmetries on the learned parameters and predictors. We first describe a…

Machine Learning · Computer Science 2023-02-10 Karl Hajjar , Lenaic Chizat

We take a Bayesian perspective to illustrate a connection between training speed and the marginal likelihood in linear models. This provides two major insights: first, that a measure of a model's training speed can be used to estimate its…

Machine Learning · Computer Science 2020-10-28 Clare Lyle , Lisa Schut , Binxin Ru , Yarin Gal , Mark van der Wilk

We prove that for an $L$-layer fully-connected linear neural network, if the width of every hidden layer is $\tilde\Omega (L \cdot r \cdot d_{\mathrm{out}} \cdot \kappa^3 )$, where $r$ and $\kappa$ are the rank and the condition number of…

Machine Learning · Computer Science 2019-05-28 Simon S. Du , Wei Hu

Neural networks trained via gradient descent with random initialization and without any regularization enjoy good generalization performance in practice despite being highly overparametrized. A promising direction to explain this phenomenon…

Machine Learning · Computer Science 2022-05-17 Hancheng Min , Salma Tarmoun , Rene Vidal , Enrique Mallada