English
Related papers

Related papers: Insights from Gradient Dynamics: Gradient Autoscal…

200 papers

Modern neural networks are typically trained in an over-parameterized regime where the parameters of the model far exceed the size of the training data. Such neural networks in principle have the capacity to (over)fit any set of labels…

Machine Learning · Computer Science 2019-07-05 Mingchen Li , Mahdi Soltanolkotabi , Samet Oymak

Stochastic gradient descent (SGD) and adaptive gradient methods, such as Adam and RMSProp, have been widely used in training deep neural networks. We empirically show that while the difference between the standard generalization performance…

Machine Learning · Computer Science 2023-11-30 Avery Ma , Yangchen Pan , Amir-massoud Farahmand

Gradient descent and stochastic gradient descent are central to modern machine learning, yet their behavior under large step sizes remains theoretically unclear. Recent work suggests that acceleration often arises near the edge of…

Machine Learning · Computer Science 2026-03-02 Sacchit Kale , Piyushi Manupriya , Pierre Marion , Francis Bach , Anant Raj

In this paper we develop a new perspective on generalization of neural networks by proposing and investigating the concept of a neural network stiffness. We measure how stiff a network is by looking at how a small gradient step in the…

Machine Learning · Computer Science 2020-03-17 Stanislav Fort , Paweł Krzysztof Nowak , Stanislaw Jastrzebski , Srini Narayanan

Human beings can quickly adapt to environmental changes by leveraging learning experience. However, adapting deep neural networks to dynamic environments by machine learning algorithms remains a challenge. To better understand this issue,…

Computer Vision and Pattern Recognition · Computer Science 2021-03-24 Shixiang Tang , Peng Su , Dapeng Chen , Wanli Ouyang

We propose a new regularization method to alleviate over-fitting in deep neural networks. The key idea is utilizing randomly transformed training samples to regularize a set of sub-networks, which are originated by sampling the width of the…

Computer Vision and Pattern Recognition · Computer Science 2020-10-14 Taojiannan Yang , Sijie Zhu , Chen Chen

Gradient descent dynamics on the deep matrix factorization problem is extensively studied as a simplified theoretical model for deep neural networks. Although the convergence theory for two-layer matrix factorization is well-established, no…

Optimization and Control · Mathematics 2025-11-20 Minrui Luo , Weihang Xu , Xiang Gao , Maryam Fazel , Simon Shaolei Du

Recent network pruning methods focus on pruning models early-on in training. To estimate the impact of removing a parameter, these methods use importance measures that were originally designed to prune trained models. Despite lacking…

Machine Learning · Computer Science 2021-09-24 Ekdeep Singh Lubana , Robert P. Dick

Large-scale distributed training of deep neural networks results in models with worse generalization performance as a result of the increase in the effective mini-batch size. Previous approaches attempt to address this problem by varying…

Machine Learning · Computer Science 2020-02-17 Kazuki Osawa , Yohei Tsuji , Yuichiro Ueno , Akira Naruse , Chuan-Sheng Foo , Rio Yokota

As deep neural networks are highly expressive, it is important to find solutions with small generalization gap (the difference between the performance on the training data and unseen data). Focusing on the stochastic nature of training, we…

Machine Learning · Computer Science 2023-10-31 Rie Johnson , Tong Zhang

Gradient descent finds a global minimum in training deep neural networks despite the objective function being non-convex. The current paper proves gradient descent achieves zero training loss in polynomial time for a deep over-parameterized…

Machine Learning · Computer Science 2019-05-30 Simon S. Du , Jason D. Lee , Haochuan Li , Liwei Wang , Xiyu Zhai

A recent line of work has established intriguing connections between the generalization/compression properties of a deep neural network (DNN) model and the so-called layer weights' stable ranks. Intuitively, the latter are indicators of the…

Machine Learning · Computer Science 2021-10-07 Bogdan Georgiev , Lukas Franken , Mayukh Mukherjee , Georgios Arvanitidis

Graph convolutional networks (GCNs) have emerged as powerful models for graph learning tasks, exhibiting promising performance in various domains. While their empirical success is evident, there is a growing need to understand their…

Machine Learning · Computer Science 2025-09-30 Guangrui Yang , Ming Li , Han Feng , Xiaosheng Zhuang

In machine learning, there is a fundamental trade-off between ease of optimization and expressive power. Neural Networks, in particular, have enormous expressive power and yet are notoriously challenging to train. The nature of that…

Machine Learning · Computer Science 2015-11-24 Diogo Almeida , Nate Sauder

We study the convergence of gradient flow for the training of deep neural networks. If Residual Neural Networks are a popular example of very deep architectures, their training constitutes a challenging optimization problem due notably to…

Machine Learning · Computer Science 2025-07-22 Raphaël Barboni , Gabriel Peyré , François-Xavier Vialard

Modern deep learning models generalize remarkably well in-distribution, despite being overparametrized and trained with little to no explicit regularization. Instead, current theory credits implicit regularization imposed by the choice of…

Machine Learning · Computer Science 2026-03-17 Jonathan Wenger , Beau Coker , Juraj Marusic , John P. Cunningham

Vanishing and exploding gradients are two of the main obstacles in training deep neural networks, especially in capturing long range dependencies in recurrent neural networks~(RNNs). In this paper, we present an efficient parametrization of…

Machine Learning · Computer Science 2018-03-28 Jiong Zhang , Qi Lei , Inderjit S. Dhillon

This paper presents a novel optimization method for maximizing generalization over tasks in meta-learning. The goal of meta-learning is to learn a model for an agent adapting rapidly when presented with previously unseen tasks. Tasks are…

Machine Learning · Computer Science 2018-10-19 Amir Erfan Eshratifar , David Eigen , Massoud Pedram

We identify and formalize a fundamental gradient descent phenomenon resulting in a learning proclivity in over-parameterized neural networks. Gradient Starvation arises when cross-entropy loss is minimized by capturing only a subset of…

Machine Learning · Computer Science 2021-11-25 Mohammad Pezeshki , Sékou-Oumar Kaba , Yoshua Bengio , Aaron Courville , Doina Precup , Guillaume Lajoie

In real-life applications, machine learning models often face scenarios where there is a change in data distribution between training and test domains. When the aim is to make predictions on distributions different from those seen at…

Machine Learning · Computer Science 2021-11-04 Lucas Mansilla , Rodrigo Echeveste , Diego H. Milone , Enzo Ferrante