English
Related papers

Related papers: Three Mechanisms of Weight Decay Regularization

200 papers

Despite huge successes on a wide range of tasks, neural networks are known to sometimes struggle to generalise to unseen data. Many approaches have been proposed over the years to promote the generalisation ability of neural networks,…

Machine Learning · Computer Science 2026-02-02 Christiaan P. Opperman , Anna S. Bosman , Katherine M. Malan

In modern deep learning, weight decay is often credited with "stabilizing" training dynamics, diverging from its classical role as a static regularization penalty. We investigate a fundamental question: *does weight decay stabilize training…

Machine Learning · Computer Science 2026-05-19 Marius Saether , Amir Kolic , Tomaso Poggio , Pierfrancesco Beneventano

Effective regularisation of neural networks is essential to combat overfitting due to the large number of parameters involved. We present an empirical analogue to the Lipschitz constant of a feed-forward neural network, which we refer to as…

Machine Learning · Statistics 2018-07-03 Henry Gouk , Bernhard Pfahringer , Eibe Frank , Michael Cree

A neural network regularizer (e.g., weight decay) boosts performance by explicitly penalizing the complexity of a network. In this paper, we penalize inferior network activations -- feature embeddings -- which in turn regularize the…

Computer Vision and Pattern Recognition · Computer Science 2021-03-05 Ahmed Taha , Alex Hanson , Abhinav Shrivastava , Larry Davis

We challenge the prevailing view that weight oscillations observed during Quantization Aware Training (QAT) are merely undesirable side-effects and argue instead that they are an essential part of QAT. We show in a univariate linear model…

Machine Learning · Computer Science 2025-12-10 Jonathan Wenshøj , Bob Pepin , Raghavendra Selvan

Implicit bias plays an important role in explaining how overparameterized models generalize well. Explicit regularization like weight decay is often employed in addition to prevent overfitting. While both concepts have been studied…

Machine Learning · Computer Science 2025-08-25 Tom Jacobs , Chao Zhou , Rebekka Burkholz

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

Convolutional neural network training can suffer from diverse issues like exploding or vanishing gradients, scaling-based weight space symmetry and covariant-shift. In order to address these issues, researchers develop weight regularization…

Computer Vision and Pattern Recognition · Computer Science 2021-03-12 Theodoros Georgiou , Sebastian Schmitt , Thomas Bäck , Wei Chen , Michael Lew

Despite perfectly interpolating the training data, deep neural networks (DNNs) can often generalize fairly well, in part due to the "implicit regularization" induced by the learning algorithm. Nonetheless, various forms of regularization,…

Machine Learning · Computer Science 2022-02-23 Navid Azizan , Sahin Lale , Babak Hassibi

Quantization of neural networks has become common practice, driven by the need for efficient implementations of deep neural networks on embedded devices. In this paper, we exploit an oft-overlooked degree of freedom in most networks - for a…

Machine Learning · Computer Science 2019-02-07 Eldad Meller , Alexander Finkelstein , Uri Almog , Mark Grobman

We analyze gradient descent with randomly weighted data points in a linear regression model, under a generic weighting distribution. This includes various forms of stochastic gradient descent, importance sampling, but also extends to…

Machine Learning · Statistics 2025-12-12 Gabriel Clara , Yazan Mash'al

Deep Neural Networks reached state-of-the-art performance across numerous domains, but this progress has come at the cost of increasingly large and over-parameterized models, posing serious challenges for deployment on resource-constrained…

Machine Learning · Computer Science 2026-02-04 Dario Malchiodi , Mattia Ferraretto , Marco Frasca

Dropout is a regularization technique widely used in training artificial neural networks to mitigate overfitting. It consists of dynamically deactivating subsets of the network during training to promote more robust representations. Despite…

Machine Learning · Statistics 2025-09-10 Francesco Mori , Francesca Mignacco

Normalization methods such as batch [Ioffe and Szegedy, 2015], weight [Salimansand Kingma, 2016], instance [Ulyanov et al., 2016], and layer normalization [Baet al., 2016] have been widely used in modern machine learning. Here, we study the…

Machine Learning · Computer Science 2022-08-31 Xiaoxia Wu , Edgar Dobriban , Tongzheng Ren , Shanshan Wu , Zhiyuan Li , Suriya Gunasekar , Rachel Ward , Qiang Liu

Data augmentation that introduces diversity into the input data has long been used in training deep learning models. It has demonstrated benefits in improving robustness and generalization, practically aligning well with other…

Machine Learning · Computer Science 2025-08-18 Yang Ba , Michelle V. Mancenido , Rong Pan

Many failures in deep continual and reinforcement learning are associated with increasing magnitudes of the weights, making them hard to change and potentially causing overfitting. While many methods address these learning failures, they…

Machine Learning · Computer Science 2024-07-03 Mohamed Elsayed , Qingfeng Lan , Clare Lyle , A. Rupam Mahmood

Loss of plasticity, trainability loss, and primacy bias have been identified as issues arising when training deep neural networks on sequences of tasks -- all referring to the increased difficulty in training on new tasks. We propose to use…

Machine Learning · Computer Science 2024-12-11 Wesley Chung , Lynn Cherif , David Meger , Doina Precup

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 aim of this paper is to introduce two widely applicable regularization methods based on the direct modification of weight matrices. The first method, Weight Reinitialization, utilizes a simplified Bayesian assumption with partially…

Machine Learning · Computer Science 2022-06-07 Patrik Reizinger , Bálint Gyires-Tóth

We propose an empirical approach centered on the spectral dynamics of weights -- the behavior of singular values and vectors during optimization -- to unify and clarify several phenomena in deep learning. We identify a consistent bias in…