English
Related papers

Related papers: Early Directional Convergence in Deep Homogeneous …

200 papers

In this work, we investigate a particular implicit bias in gradient descent training, which we term "Feature Averaging," and argue that it is one of the principal factors contributing to the non-robustness of deep neural networks. We show…

Machine Learning · Computer Science 2025-03-04 Binghui Li , Zhixuan Pan , Kaifeng Lyu , Jian Li

When optimizing over-parameterized models, such as deep neural networks, a large set of parameters can achieve zero training error. In such cases, the choice of the optimization algorithm and its respective hyper-parameters introduces…

Machine Learning · Computer Science 2019-12-06 Gauthier Gidel , Francis Bach , Simon Lacoste-Julien

Next generation deep neural networks for classification hosted on embedded platforms will rely on fast, efficient, and accurate learning algorithms. Initialization of weights in learning networks has a great impact on the classification…

Machine Learning · Computer Science 2016-07-21 Julius , Gopinath Mahale , Sumana T. , C. S. Adityakrishna

Operator learning techniques have recently emerged as a powerful tool for learning maps between infinite-dimensional Banach spaces. Trained under appropriate constraints, they can also be effective in learning the solution operator of…

Machine Learning · Computer Science 2021-10-13 Sifan Wang , Hanwen Wang , Paris Perdikaris

Machine Unlearning aims to remove specific data from trained models, addressing growing privacy and ethical concerns. We provide a theoretical analysis of a simple and widely used method - gradient ascent - used to reverse the influence of…

Machine Learning · Computer Science 2025-10-17 Odelia Melamed , Gilad Yehudai , Gal Vardi

Neural networks are discrete entities: subdivided into discrete layers and parametrized by weights which are iteratively optimized via difference equations. Recent work proposes networks with layer outputs which are no longer quantized but…

Neural and Evolutionary Computing · Computer Science 2019-09-09 Stefano Massaroli , Michael Poli , Federico Califano , Angela Faragasso , Jinkyoo Park , Atsushi Yamashita , Hajime Asama

We study the convergence of gradient descent (GD) and stochastic gradient descent (SGD) for training $L$-hidden-layer linear residual networks (ResNets). We prove that for training deep residual networks with certain linear transformations…

Machine Learning · Computer Science 2020-03-03 Difan Zou , Philip M. Long , Quanquan Gu

Deep neural networks have successfully been trained in various application areas with stochastic gradient descent. However, there exists no rigorous mathematical explanation why this works so well. The training of neural networks with…

Machine Learning · Computer Science 2021-10-13 Patrick Cheridito , Arnulf Jentzen , Florian Rossmannek

We consider a deep ReLU / Leaky ReLU student network trained from the output of a fixed teacher network of the same depth, with Stochastic Gradient Descent (SGD). The student network is \emph{over-realized}: at each layer $l$, the number…

Machine Learning · Computer Science 2020-06-30 Yuandong Tian

We examine the implicit bias of mirror flow in univariate least squares error regression with wide and shallow neural networks. For a broad class of potential functions, we show that mirror flow exhibits lazy training and has the same…

Machine Learning · Statistics 2025-03-20 Shuang Liang , Guido Montúfar

Despite the fact that the loss functions of deep neural networks are highly non-convex, gradient-based optimization algorithms converge to approximately the same performance from many random initial points. One thread of work has focused on…

Machine Learning · Computer Science 2020-03-24 Charles G. Frye , James Simon , Neha S. Wadia , Andrew Ligeralde , Michael R. DeWeese , Kristofer E. Bouchard

Biological and artificial neural networks develop internal representations that enable them to perform complex tasks. In artificial networks, the effectiveness of these models relies on their ability to build task specific representation, a…

Proper regularization is critical for speeding up training, improving generalization performance, and learning compact models that are cost efficient. We propose and analyze regularized gradient descent algorithms for learning shallow…

Machine Learning · Computer Science 2018-06-08 Samet Oymak

An interesting approach to analyzing neural networks that has received renewed attention is to examine the equivalent kernel of the neural network. This is based on the fact that a fully connected feedforward network with one hidden layer,…

Machine Learning · Computer Science 2018-06-04 Russell Tsuchida , Farbod Roosta-Khorasani , Marcus Gallagher

We analyze recurrent neural networks with diagonal hidden-to-hidden weight matrices, trained with gradient descent in the supervised learning setting, and prove that gradient descent can achieve optimality \emph{without} massive…

Machine Learning · Computer Science 2024-10-11 Semih Cayci , Atilla Eryilmaz

A recent series of theoretical works showed that the dynamics of neural networks with a certain initialisation are well-captured by kernel methods. Concurrent empirical work demonstrated that kernel methods can come close to the performance…

Machine Learning · Computer Science 2021-06-11 Maria Refinetti , Sebastian Goldt , Florent Krzakala , Lenka Zdeborová

We study approximation and statistical learning properties of deep ReLU networks under structural assumptions that mitigate the curse of dimensionality. We prove minimax-optimal uniform approximation rates for $s$-H\"older smooth functions…

Statistics Theory · Mathematics 2026-02-06 Thomas Nagler , Sophie Langer

Understanding the asymptotic behavior of gradient-descent training of deep neural networks is essential for revealing inductive biases and improving network performance. We derive the infinite-time training limit of a mathematically…

Machine Learning · Statistics 2022-02-08 Samuel Lippl , L. F. Abbott , SueYeon Chung

Diagonal linear networks (DLNs) are a tractable model that captures several nontrivial behaviors in neural network training, such as initialization-dependent solutions and incremental learning. These phenomena are typically studied in…

Machine Learning · Statistics 2026-03-16 Sota Nishiyama , Masaaki Imaizumi

Neural network training is inherently sensitive to initialization and the randomness induced by stochastic gradient descent. However, it is unclear to what extent such effects lead to meaningfully different networks, either in terms of the…

Machine Learning · Computer Science 2025-06-17 Devin Kwok , Gül Sena Altıntaş , Colin Raffel , David Rolnick