English
Related papers

Related papers: Gradient Clipping Beyond Vector Norms: A Spectral …

200 papers

In this paper, the problem of distributed optimization is studied via a network of agents. Each agent only has access to a noisy gradient of its own objective function, and can communicate with its neighbors via a network. To handle this…

Optimization and Control · Mathematics 2025-06-19 Yuchen Yang , Kaihong Lu , Long Wang

The architecture and the parameters of neural networks are often optimized independently, which requires costly retraining of the parameters whenever the architecture is modified. In this work we instead focus on growing the architecture…

Machine Learning · Computer Science 2022-06-08 Utku Evci , Bart van Merriënboer , Thomas Unterthiner , Max Vladymyrov , Fabian Pedregosa

Gradient dynamics play a central role in determining the stability and generalization of deep neural networks. In this work, we provide an empirical analysis of how variance and standard deviation of gradients evolve during training,…

Machine Learning · Computer Science 2025-09-09 Vincent-Daniel Yun

This work introduces a hybrid non-Euclidean optimization method which generalizes gradient norm clipping by combining steepest descent and conditional gradient approaches. The method achieves the best of both worlds by establishing a…

Machine Learning · Computer Science 2026-02-05 Thomas Pethick , Wanyun Xie , Mete Erdogan , Kimon Antonakopoulos , Antonio Silveti-Falls , Volkan Cevher

A number of results have recently demonstrated the benefits of incorporating various constraints when training deep architectures in vision and machine learning. The advantages range from guarantees for statistical generalization to better…

Machine Learning · Computer Science 2019-05-27 Sathya N. Ravi , Tuan Dinh , Vishnu Lokhande , Vikas Singh

Heavy-tailed noise is pervasive in modern machine learning applications, arising from data heterogeneity, outliers, and non-stationary stochastic environments. While second-order methods can significantly accelerate convergence in…

Optimization and Control · Mathematics 2025-10-14 Abdurakhmon Sadiev , Peter Richtárik , Ilyas Fatkhullin

In this work, we study the convergence \emph{in high probability} of clipped gradient methods when the noise distribution has heavy tails, ie., with bounded $p$th moments, for some $1<p\le2$. Prior works in this setting follow the same…

Optimization and Control · Mathematics 2023-04-05 Ta Duy Nguyen , Alina Ene , Huy L. Nguyen

Deep neural networks (DNNs) have set benchmarks on a wide array of supervised learning tasks. Trained DNNs, however, often lack robustness to minor adversarial perturbations to the input, which undermines their true practicality. Recent…

Machine Learning · Computer Science 2018-11-20 Farzan Farnia , Jesse M. Zhang , David Tse

There are two widely known issues with properly training Recurrent Neural Networks, the vanishing and the exploding gradient problems detailed in Bengio et al. (1994). In this paper we attempt to improve the understanding of the underlying…

Machine Learning · Computer Science 2013-02-19 Razvan Pascanu , Tomas Mikolov , Yoshua Bengio

A widely believed explanation for the remarkable generalization capacities of overparameterized neural networks is that the optimization algorithms used for training induce an implicit bias towards benign solutions. To grasp this…

Machine Learning · Computer Science 2025-12-19 Maria Matveev , Vit Fojtik , Hung-Hsu Chou , Gitta Kutyniok , Johannes Maly

We consider stochastic convex optimization for heavy-tailed data with the guarantee of being differentially private (DP). Most prior works on differentially private stochastic convex optimization for heavy-tailed data are either restricted…

Machine Learning · Computer Science 2024-09-11 Chenhan Jin , Kaiwen Zhou , Bo Han , James Cheng , Tieyong Zeng

In existing distributed stochastic optimization studies, it is usually assumed that the gradient noise has a bounded variance. However, recent research shows that the heavy-tailed noise, which allows an unbounded variance, is closer to…

Optimization and Control · Mathematics 2025-05-15 Jun Hu , Chao Sun , Bo Chen , Jianzheng Wang , Zheming Wang

The big breakthrough on the ImageNet challenge in 2012 was partially due to the `dropout' technique used to avoid overfitting. Here, we introduce a new approach called `Spectral Dropout' to improve the generalization ability of deep neural…

Computer Vision and Pattern Recognition · Computer Science 2017-11-27 Salman Khan , Munawar Hayat , Fatih Porikli

We study nonparametric regression by an over-parameterized two-layer neural network trained by gradient descent (GD) in this paper. We show that, if the neural network is trained by GD with early stopping, then the trained network renders a…

Machine Learning · Statistics 2025-11-07 Yingzhen Yang , Ping Li

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

Gradient normalization and soft clipping are two popular techniques for tackling instability issues and improving convergence of stochastic gradient descent (SGD) with momentum. In this article, we study these types of methods through the…

Optimization and Control · Mathematics 2025-07-01 Måns Williamson , Tony Stillfjord

Differential privacy (DP) has become a prevalent privacy model in a wide range of machine learning tasks, especially after the debut of DP-SGD. However, DP-SGD, which directly perturbs gradients in the training iterations, fails to mitigate…

Machine Learning · Computer Science 2025-04-09 Jiawei Duan , Haibo Hu , Qingqing Ye , Xinyue Sun

Deep feedforward and recurrent networks have achieved impressive results in many perception and language processing applications. This success is partially attributed to architectural innovations such as convolutional and long short-term…

Machine Learning · Statistics 2015-11-24 Arvind Neelakantan , Luke Vilnis , Quoc V. Le , Ilya Sutskever , Lukasz Kaiser , Karol Kurach , James Martens

Regularizing the gradient norm of the output of a neural network with respect to its inputs is a powerful technique, rediscovered several times. This paper presents evidence that gradient regularization can consistently improve…

Machine Learning · Computer Science 2018-05-28 Dániel Varga , Adrián Csiszárik , Zsolt Zombori

Gradient compression has surfaced as a key technique to address the challenge of communication efficiency in distributed learning. In distributed deep learning, however, it is observed that gradient distributions are heavy-tailed, with…

Machine Learning · Computer Science 2024-02-07 Guangfeng Yan , Tan Li , Yuanzhang Xiao , Hanxu Hou , Linqi Song
‹ Prev 1 4 5 6 7 8 10 Next ›