English
Related papers

Related papers: Why Do We Need Weight Decay in Modern Deep Learnin…

200 papers

Deep reinforcement learning (RL) suffers from plasticity loss severely due to the nature of non-stationarity, which impairs the ability to adapt to new data and learn continually. Unfortunately, our understanding of how plasticity loss…

Machine Learning · Computer Science 2026-04-03 Zihao Wu , Hongyao Tang , Yi Ma , Jiashun Liu , Yan Zheng , Jianye Hao

The history of deep learning has shown that human-designed problem-specific networks can greatly improve the classification performance of general neural models. In most practical cases, however, choosing the optimal architecture for a…

Machine Learning · Computer Science 2020-09-14 Nicolo Colombo , Yang Gao

Convolutional networks are ubiquitous in deep learning. They are particularly useful for images, as they reduce the number of parameters, reduce training time, and increase accuracy. However, as a model of the brain they are seriously…

Machine Learning · Computer Science 2022-01-19 Roman Pogodin , Yash Mehta , Timothy P. Lillicrap , Peter E. Latham

Adaptive gradient methods such as Adam have gained increasing popularity in deep learning optimization. However, it has been observed that compared with (stochastic) gradient descent, Adam can converge to a different solution with a…

Machine Learning · Computer Science 2021-08-26 Difan Zou , Yuan Cao , Yuanzhi Li , Quanquan Gu

Underpinning the past decades of work on the design, initialization, and optimization of neural networks is a seemingly innocuous assumption: that the network is trained on a \textit{stationary} data distribution. In settings where this…

Machine Learning · Computer Science 2024-03-01 Clare Lyle , Zeyu Zheng , Khimya Khetarpal , Hado van Hasselt , Razvan Pascanu , James Martens , Will Dabney

The merits of fast convergence and potentially better performance of the weight normalization family have drawn increasing attention in recent years. These methods use standardization or normalization that changes the weight…

Machine Learning · Computer Science 2019-11-15 Li Xiang , Chen Shuo , Xia Yan , Yang Jian

Generalization of deep neural networks remains one of the main open problems in machine learning. Previous theoretical works focused on deriving tight bounds of model complexity, while empirical works revealed that neural networks exhibit…

Machine Learning · Computer Science 2022-01-31 James Wang , Cheng-Lin Yang

With the accumulation of resources in the era of big data and the rise of pre-trained models in deep learning, optimizing neural networks for various tasks often involves different strategies for fine-tuning pre-trained models versus…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Xin Ning , Qiankun Li , Xiaolong Huang , Qiupu Chen , Feng He , Weijun Li , Prayag Tiwari , Xinwang Liu

Training deep neural networks is a highly nontrivial task, involving carefully selecting appropriate training algorithms, scheduling step sizes and tuning other hyperparameters. Trying different combinations can be quite labor-intensive and…

Machine Learning · Computer Science 2017-06-13 Kaifeng Lv , Shunhua Jiang , Jian Li

The prevailing paradigm in large language model (LLM) development is to pretrain a base model, then perform further training to improve performance and model behavior. However, hyperparameter optimization and scaling laws have been studied…

Machine Learning · Computer Science 2026-02-12 Tessa Han , Sebastian Bordt , Hanlin Zhang , Sham Kakade

Batch normalization is currently the most widely used variant of internal normalization for deep neural networks. Additional work has shown that the normalization of weights and additional conditioning as well as the normalization of…

Computer Vision and Pattern Recognition · Computer Science 2021-01-19 Wolfgang Fuhl , Enkelejda Kasneci

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

Re-initializing a neural network during training has been observed to improve generalization in recent works. Yet it is neither widely adopted in deep learning practice nor is it often used in state-of-the-art training protocols. This…

Machine Learning · Computer Science 2023-04-04 Sheheryar Zaidi , Tudor Berariu , Hyunjik Kim , Jörg Bornschein , Claudia Clopath , Yee Whye Teh , Razvan Pascanu

Stochastic gradient descent (SGD) has been the dominant optimization method for training deep neural networks due to its many desirable properties. One of the more remarkable and least understood quality of SGD is that it generalizes…

Machine Learning · Computer Science 2020-07-03 Erhan Bilal

Memorization of training data is an active research area, yet our understanding of the inner workings of neural networks is still in its infancy. Recently, Haim et al. (2022) proposed a scheme to reconstruct training samples from multilayer…

Machine Learning · Computer Science 2023-11-06 Gon Buzaglo , Niv Haim , Gilad Yehudai , Gal Vardi , Yakir Oz , Yaniv Nikankin , Michal Irani

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

The largely successful method of training neural networks is to learn their weights using some variant of stochastic gradient descent (SGD). Here, we show that the solutions found by SGD can be further improved by ensembling a subset of the…

We explore the low-rank structure of the weight matrices in neural networks at the stationary points (limiting solutions of optimization algorithms) with $L2$ regularization (also known as weight decay). We show several properties of such…

Machine Learning · Computer Science 2025-08-21 Ilja Kuzborskij , Yasin Abbasi Yadkori

Convolutional neural networks (CNN) play a major role in image processing tasks like image classification, object detection, semantic segmentation. Very often CNN networks have from several to hundred stacked layers with several megabytes…

Machine Learning · Computer Science 2020-02-18 Marcin Pietron , Maciej Wielgosz

In deep multi-task learning, weights of task-specific networks are shared between tasks to improve performance on each single one. Since the question, which weights to share between layers, is difficult to answer, human-designed…

Machine Learning · Computer Science 2020-03-24 Jonas Prellberg , Oliver Kramer