English
Related papers

Related papers: Decoupled Weight Decay for Any $p$ Norm

200 papers

Sparse regularization techniques are well-established in machine learning, yet their application in neural networks remains challenging due to the non-differentiability of penalties like the $L_1$ norm, which is incompatible with stochastic…

Machine Learning · Computer Science 2025-02-10 Chris Kolb , Tobias Weber , Bernd Bischl , David Rügamer

In this paper, we study norm-based regularization methods for neural networks. We compare existing penalization approaches and introduce two regularization strategies that extend classical ridge- and lasso-type penalties to neural network…

Machine Learning · Statistics 2026-05-04 Muhammad Qasim , Farrukh Javed

Weight decay is one of the most widely used forms of regularization in deep learning, and has been shown to improve generalization and robustness. The optimization objective driving weight decay is a sum of losses plus a term proportional…

Machine Learning · Computer Science 2023-07-07 Liu Yang , Jifan Zhang , Joseph Shenouda , Dimitris Papailiopoulos , Kangwook Lee , Robert D. Nowak

Over the past few years, Batch-Normalization has been commonly used in deep networks, allowing faster training and high performance for a wide variety of applications. However, the reasons behind its merits remained unanswered, with several…

Machine Learning · Statistics 2019-02-08 Elad Hoffer , Ron Banner , Itay Golan , Daniel Soudry

Deep neural networks achieve state-of-the-art results on several tasks while increasing in complexity. It has been shown that neural networks can be pruned during training by imposing sparsity inducing regularizers. In this paper, we…

Machine Learning · Statistics 2019-08-12 Chaithanya Kumar Mummadi , Tim Genewein , Dan Zhang , Thomas Brox , Volker Fischer

This paper addresses the topic of sparsifying deep neural networks (DNN's). While DNN's are powerful models that achieve state-of-the-art performance on a large number of tasks, the large number of model parameters poses serious storage and…

Machine Learning · Computer Science 2018-02-07 Igor Fedorov , Bhaskar D. Rao

Batch Normalization is a commonly used trick to improve the training of deep neural networks. These neural networks use L2 regularization, also called weight decay, ostensibly to prevent overfitting. However, we show that L2 regularization…

Machine Learning · Computer Science 2017-06-19 Twan van Laarhoven

Sparse view computed tomography (CT) reconstruction poses a challenging ill-posed inverse problem, necessitating effective regularization techniques. In this letter, we employ $L_p$-norm ($0<p<1$) regularization to induce sparsity and…

Image and Video Processing · Electrical Eng. & Systems 2024-08-14 Yu Guo , Caiying Wu , Yaxin Li , Qiyu Jin , Tieyong Zeng

Sparse optimization is a fundamental challenge in various practical applications. A popular approach to sparse optimization is $\ell_p$ regularization. However, it may encounter optimization instability due to the unbounded gradients when…

Machine Learning · Computer Science 2026-05-29 Huangyu Xu , Jingqin Yang , Qianqian Xu , Jiaye Teng

Weight decay is often used to ensure good generalization in the training practice of deep neural networks with batch normalization (BN-DNNs), where some convolution layers are invariant to weight rescaling due to the normalization. In this…

Machine Learning · Computer Science 2022-06-22 Ziquan Liu , Yufei Cui , Jia Wan , Yu Mao , Antoni B. Chan

Despite recent advances, developing general-purpose universal denoising and artifact-removal networks remains largely an open problem: Given fixed network weights, one inherently trades-off specialization at one task (e.g.,~removing Poisson…

Computer Vision and Pattern Recognition · Computer Science 2024-11-19 Kevin Zhang , Sakshum Kulshrestha , Christopher Metzler

We prove linear convergence of gradient descent to a global optimum for the training of deep residual networks with constant layer width and smooth activation function. We show that if the trained weights, as a function of the layer index,…

Machine Learning · Computer Science 2023-01-26 Rama Cont , Alain Rossier , RenYuan Xu

Sparsification of neural networks is one of the effective complexity reduction methods to improve efficiency and generalizability. We consider the problem of learning a one hidden layer convolutional neural network with ReLU activation…

Optimization and Control · Mathematics 2020-02-26 Thu Dinh , Jack Xin

A major challenge in training deep neural networks is overfitting, i.e. inferior performance on unseen test examples compared to performance on training examples. To reduce overfitting, stochastic regularization methods have shown superior…

Neural and Evolutionary Computing · Computer Science 2018-04-24 Najeeb Khan , Jawad Shah , Ian Stavness

In this work, we leverage advances in sparse coding techniques to reduce the number of trainable parameters in a fully connected neural network. While most of the works in literature impose $\ell_1$ regularization, DropOut or DropConnect…

Machine Learning · Computer Science 2019-07-04 Arman Hasanzadeh , Nagaraj T. Janakiraman , Vamsi K. Amalladinne , Krishna R. Narayanan

Among the most successful methods for sparsifying deep (neural) networks are those that adaptively mask the network weights throughout training. By examining this masking, or dropout, in the linear case, we uncover a duality between such…

Machine Learning · Computer Science 2022-01-04 Daniel LeJeune , Hamid Javadi , Richard G. Baraniuk

Sparsification of neural networks is one of the effective complexity reduction methods to improve efficiency and generalizability. Binarized activation offers an additional computational saving for inference. Due to vanishing gradient issue…

Optimization and Control · Mathematics 2019-02-12 Thu Dinh , Jack Xin

Sparse training is a natural idea to accelerate the training speed of deep neural networks and save the memory usage, especially since large modern neural networks are significantly over-parameterized. However, most of the existing methods…

Machine Learning · Computer Science 2021-11-11 Xiao Zhou , Weizhong Zhang , Zonghao Chen , Shizhe Diao , Tong Zhang

Deep learning has been wildly successful in practice and most state-of-the-art machine learning methods are based on neural networks. Lacking, however, is a rigorous mathematical theory that adequately explains the amazing performance of…

Machine Learning · Statistics 2023-10-03 Rahul Parhi , Robert D. Nowak

We propose a novel multi-layer neural network architecture that gives a promising neural network empowered optimization approach to the image restoration problem. The proposed architecture is motivated by the recent study of monotone…

Optimization and Control · Mathematics 2025-10-27 Haruya Shimizu , Masahiro Yukawa