English
Related papers

Related papers: Understanding Decoupled and Early Weight Decay

200 papers

We introduce the Overfitting-Underfitting Indicator (OUI), a novel tool for monitoring the training dynamics of Deep Neural Networks (DNNs) and identifying optimal regularization hyperparameters. Specifically, we validate that OUI can…

Machine Learning · Computer Science 2025-04-25 Alberto Fernández-Hernández , Jose I. Mestre , Manuel F. Dolz , Jose Duato , Enrique S. Quintana-Ortí

In this paper, we first identify activation shift, a simple but remarkable phenomenon in a neural network in which the preactivation value of a neuron has non-zero mean that depends on the angle between the weight vector of the neuron and…

Neural and Evolutionary Computing · Computer Science 2024-03-22 Takuro Kutsuna

We investigate the inherent bias of Stochastic Gradient Descent (SGD) toward learning low-rank weight matrices during the training of deep neural networks. Our results demonstrate that training with mini-batch SGD and weight decay induces a…

Machine Learning · Computer Science 2024-10-22 Tomer Galanti , Zachary S. Siegel , Aparna Gupte , Tomaso Poggio

In this work, we comprehensively reveal the learning dynamics of neural network with normalization, weight decay (WD), and SGD (with momentum), named as Spherical Motion Dynamics (SMD). Most related works study SMD by focusing on "effective…

Machine Learning · Statistics 2020-11-30 Ruosi Wan , Zhanxing Zhu , Xiangyu Zhang , Jian Sun

Importance-weighted risk minimization is a key ingredient in many machine learning algorithms for causal inference, domain adaptation, class imbalance, and off-policy reinforcement learning. While the effect of importance weighting is…

Machine Learning · Computer Science 2019-06-17 Jonathon Byrd , Zachary C. Lipton

Value-based deep Reinforcement Learning (RL) algorithms suffer from the estimation bias primarily caused by function approximation and temporal difference (TD) learning. This problem induces faulty state-action value estimates and therefore…

Machine Learning · Computer Science 2021-11-15 Dogan C. Cicek , Enes Duran , Baturay Saglam , Kagan Kaya , Furkan B. Mutlu , Suleyman S. Kozat

Collecting the large datasets needed to train deep neural networks can be very difficult, particularly for the many applications for which sharing and pooling data is complicated by practical, ethical, or legal concerns. However, it may be…

Pruning the weights of neural networks is an effective and widely-used technique for reducing model size and inference complexity. We develop and test a novel method based on compressed sensing which combines the pruning and training into a…

Computer Vision and Pattern Recognition · Computer Science 2021-04-08 Jonathan W. Siegel , Jianhong Chen , Pengchuan Zhang , Jinchao Xu

Many different deep networks have been used to approximate, accelerate or improve traditional image operators. Among these traditional operators, many contain parameters which need to be tweaked to obtain the satisfactory results, which we…

Computer Vision and Pattern Recognition · Computer Science 2019-07-15 Qingnan Fan , Dongdong Chen , Lu Yuan , Gang Hua , Nenghai Yu , Baoquan Chen

Neural Collapse (NC) is a geometric structure recently observed at the terminal phase of training deep neural networks, which states that last-layer feature vectors for the same class would "collapse" to a single point, while features of…

Machine Learning · Computer Science 2024-09-06 Leyan Pan , Xinyuan Cao

We introduce a novel framework for learning in neural networks by decomposing each neuron's weight vector into two distinct parts, $W_1$ and $W_2$, thereby modeling contrastive information directly at the neuron level. Traditional gradient…

Machine Learning · Computer Science 2025-03-19 Xi Wang

This paper investigates the stochastic optimization problem with a focus on developing scalable parallel algorithms for deep learning tasks. Our solution involves a reformation of the objective function for stochastic optimization in neural…

Machine Learning · Computer Science 2020-04-09 Pengzhan Guo , Zeyang Ye , Keli Xiao , Wei Zhu

Depthwise separable convolution has shown great efficiency in network design, but requires time-consuming training procedure with full training-set available. This paper first analyzes the mathematical relationship between regular…

Computer Vision and Pattern Recognition · Computer Science 2018-08-17 Jianbo Guo , Yuxi Li , Weiyao Lin , Yurong Chen , Jianguo Li

Incorporating encoding-decoding nets with adversarial nets has been widely adopted in image generation tasks. We observe that the state-of-the-art achievements were obtained by carefully balancing the reconstruction loss and adversarial…

Computer Vision and Pattern Recognition · Computer Science 2018-01-23 Zhifei Zhang , Yang Song , Hairong Qi

The weight decay regularization term is widely used during training to constrain expressivity, avoid overfitting, and improve generalization. Historically, this concept was borrowed from the SVM maximum margin principle and extended to…

Machine Learning · Computer Science 2021-10-12 Berry Weinstein , Shai Fine , Yacov Hel-Or

Weight decay remains one of the most widely used regularization mechanisms for training convolutional neural networks, yet it is still commonly applied as a fixed coefficient shared by all layers throughout training. This uniform treatment…

The pressing need to reduce the capacity of deep neural networks has stimulated the development of network dilution methods and their analysis. While the ability of $L_1$ and $L_0$ regularization to encourage sparsity is often mentioned,…

Image and Video Processing · Electrical Eng. & Systems 2020-12-08 Yael Ben-Guigui , Jacob Goldberger , Tammy Riklin-Raviv

In a variational denoising model, weight in the data fidelity term plays the role of enhancing the noise-removal capability. It is profoundly correlated with noise information, while also balancing the data fidelity and regularization…

Image and Video Processing · Electrical Eng. & Systems 2026-04-14 Xiangyu Rui , Xiangyong Cao , Xile Zhao , Deyu Meng , Michael K. NG

We present weight normalization: a reparameterization of the weight vectors in a neural network that decouples the length of those weight vectors from their direction. By reparameterizing the weights in this way we improve the conditioning…

Machine Learning · Computer Science 2016-06-07 Tim Salimans , Diederik P. Kingma

Using weight decay to penalize the L2 norms of weights in neural networks has been a standard training practice to regularize the complexity of networks. In this paper, we show that a family of regularizers, including weight decay, is…

Machine Learning · Computer Science 2022-06-09 Ziquan Liu , Yufei Cui , Antoni B. Chan