English
Related papers

Related papers: Why flatness does and does not correlate with gene…

200 papers

Graph Neural Networks (GNNs) have achieved remarkable success across various graph-based tasks but remain highly sensitive to distribution shifts. In this work, we focus on a prevalent yet under-explored phenomenon in graph generalization,…

Machine Learning · Computer Science 2026-02-10 Yang Qiu , Yixiong Zou , Jun Wang

The backpropagation networks are notably susceptible to catastrophic forgetting, where networks tend to forget previously learned skills upon learning new ones. To address such the 'sensitivity-stability' dilemma, most previous efforts have…

Machine Learning · Computer Science 2021-10-12 Danruo Deng , Guangyong Chen , Jianye Hao , Qiong Wang , Pheng-Ann Heng

We study generalization in deep learning by appealing to complexity measures originally developed in approximation and information theory. While these concepts are challenged by the high-dimensional and data-defined nature of deep learning,…

Machine Learning · Statistics 2020-12-17 Abhejit Rajagopal , Vamshi C. Madala , Shivkumar Chandrasekaran , Peder E. Z. Larson

The presence of label noise in the training data has a profound impact on the generalization of deep neural networks (DNNs). In this study, we introduce and theoretically demonstrate a simple feature noise method, which directly adds noise…

Machine Learning · Computer Science 2023-08-04 Lu Zeng , Xuan Chen , Xiaoshuang Shi , Heng Tao Shen

Despite enormous successful applications of graph neural networks (GNNs), theoretical understanding of their generalization ability, especially for node-level tasks where data are not independent and identically-distributed (IID), has been…

Machine Learning · Computer Science 2021-12-01 Jiaqi Ma , Junwei Deng , Qiaozhu Mei

This paper presents a new generalization error analysis for Decentralized Stochastic Gradient Descent (D-SGD) based on algorithmic stability. The obtained results overhaul a series of recent works that suggested an increased instability due…

Machine Learning · Computer Science 2024-06-14 Batiste Le Bars , Aurélien Bellet , Marc Tommasi , Kevin Scaman , Giovanni Neglia

Previous work has examined the ability of larger capacity neural networks to generalize better than smaller ones, even without explicit regularizers, by analyzing gradient based algorithms such as GD and SGD. The presence of noise and its…

Machine Learning · Computer Science 2020-05-27 Arushi Gupta

Adaptive optimization algorithms, such as Adam and RMSprop, have shown better optimization performance than stochastic gradient descent (SGD) in some scenarios. However, recent studies show that they often lead to worse generalization…

Machine Learning · Computer Science 2018-09-19 Zijun Zhang , Lin Ma , Zongpeng Li , Chuan Wu

Even though Deep Neural Networks (DNNs) are widely celebrated for their practical performance, they possess many intriguing properties related to depth that are difficult to explain both theoretically and intuitively. Understanding how…

Machine Learning · Computer Science 2020-03-18 Christopher Snyder , Sriram Vishwanath

In this paper, we tackle the problem of training with multiple source domains with the aim to generalize to new domains at test time without an adaptation step. This is known as domain generalization (DG). Previous works on DG assume…

Computer Vision and Pattern Recognition · Computer Science 2021-04-29 Mohammad Mahfujur Rahman , Clinton Fookes , Sridha Sridharan

Sharpness-Aware Minimization (SAM) enhances generalization by reducing a Max-Sharpness (MaxS). Despite the practical success, we empirically found that the MAxS behind SAM's generalization enhancements face the "Flatness Indicator Problem"…

Computer Vision and Pattern Recognition · Computer Science 2024-09-23 Jiaxin Deng , Junbiao Pang , Baochang Zhang , Qingming Huang

We propose a new approach, called as functional deep neural network (FDNN), for classifying multi-dimensional functional data. Specifically, a deep neural network is trained based on the principle components of the training data which shall…

Machine Learning · Statistics 2022-05-19 Shuoyang Wang , Guanqun Cao , Zuofeng Shang

While deep neural networks demonstrate state-of-the-art performance on a variety of learning tasks, their performance relies on the assumption that train and test distributions are the same, which may not hold in real-world applications.…

Machine Learning · Computer Science 2021-02-18 Wenyu Zhang , Mohamed Ragab , Ramon Sagarna

It is arguably believed that flatter minima can generalize better. However, it has been pointed out that the usual definitions of sharpness, which consider either the maxima or the integral of loss over a $\delta$ ball of parameters around…

Machine Learning · Computer Science 2021-01-11 Mingyang Yi , Huishuai Zhang , Wei Chen , Zhi-Ming Ma , Tie-Yan Liu

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

During the past decade, deep neural networks have led to fast-paced progress and significant achievements in computer vision problems, for both academia and industry. Yet despite their success, state-of-the-art image classification…

Computer Vision and Pattern Recognition · Computer Science 2024-05-13 Aristotelis Ballas , Christos Diou

We perform an experimental study of the dynamics of Stochastic Gradient Descent (SGD) in learning deep neural networks for several real and synthetic classification tasks. We show that in the initial epochs, almost all of the performance…

Machine Learning · Computer Science 2019-05-29 Preetum Nakkiran , Gal Kaplun , Dimitris Kalimeris , Tristan Yang , Benjamin L. Edelman , Fred Zhang , Boaz Barak

Recent research on the grokking phenomenon has illuminated the intricacies of neural networks' training dynamics and their generalization behaviors. Grokking refers to a sharp rise of the network's generalization accuracy on the test set,…

Machine Learning · Computer Science 2024-05-31 Simin Fan , Razvan Pascanu , Martin Jaggi

In the past decade, significant strides in deep learning have led to numerous groundbreaking applications. Despite these advancements, the understanding of the high generalizability of deep learning, especially in such an over-parametrized…

Disordered Systems and Neural Networks · Physics 2024-09-17 Hao Liao , Wei Zhang , Zhanyi Huang , Zexiao Long , Mingyang Zhou , Xiaoqun Wu , Rui Mao , Chi Ho Yeung

The concept of sharpness has been successfully applied to traditional architectures like MLPs and CNNs to predict their generalization. For transformers, however, recent work reported weak correlation between flatness and generalization. We…

Machine Learning · Computer Science 2025-05-09 Marvin F. da Silva , Felix Dangel , Sageev Oore