English
Related papers

Related papers: Three Mechanisms of Weight Decay Regularization

200 papers

Deep Neural Networks have achieved remarkable success relying on the developing availability of GPUs and large-scale datasets with increasing network depth and width. However, due to the expensive computation and intensive memory,…

Machine Learning · Computer Science 2020-09-07 E Zhenqian , Gao Weiguo

This paper investigates theoretical properties and efficient numerical algorithms for the so-called elastic-net regularization originating from statistics, which enforces simultaneously l^1 and l^2 regularization. The stability of the…

Numerical Analysis · Mathematics 2015-05-13 Bangti Jin , Dirk Lorenz , Stefan Schiffler

Several image processing tasks, such as image classification and object detection, have been significantly improved using Convolutional Neural Networks (CNN). Like ResNet and EfficientNet, many architectures have achieved outstanding…

Computer Vision and Pattern Recognition · Computer Science 2022-01-11 Claudio Filipi Gonçalves dos Santos , João Paulo Papa

Regularization for optimization is a crucial technique to avoid overfitting in machine learning. In order to obtain the best performance, we usually train a model by tuning the regularization parameters. It becomes costly, however, when a…

Machine Learning · Computer Science 2020-08-18 Jingfeng Wu , Vladimir Braverman , Lin F. Yang

Although overparameterized models have achieved remarkable practical success, their theoretical properties, particularly their generalization behavior, remain incompletely understood. The well known double descents phenomenon suggests that…

Machine Learning · Statistics 2026-01-06 Haoran Zhan , Yingcun Xia

With the success of deep neural networks (NNs) in a variety of domains, the computational and storage requirements for training and deploying large NNs have become a bottleneck for further improvements. Sparsification has consequently…

Machine Learning · Computer Science 2024-04-24 Nadav Joseph Outmezguine , Noam Levi

This paper analyzes regularization terms proposed recently for improving the adversarial robustness of deep neural networks (DNNs), from a theoretical point of view. Specifically, we study possible connections between several effective…

Machine Learning · Computer Science 2020-07-07 Yiwen Guo , Long Chen , Yurong Chen , Changshui Zhang

We study the statistical performance of a continual learning problem with two linear regression tasks in a well-specified random design setting. We consider a structural regularization algorithm that incorporates a generalized…

Machine Learning · Computer Science 2025-04-08 Haoran Li , Jingfeng Wu , Vladimir Braverman

There is a significant performance gap between Binary Neural Networks (BNNs) and floating point Deep Neural Networks (DNNs). We propose to improve the binary training method, by introducing a new regularization function that encourages…

Machine Learning · Computer Science 2020-04-22 Sajad Darabi , Mouloud Belbahri , Matthieu Courbariaux , Vahid Partovi Nia

We investigate the generalizability of deep learning based on the sensitivity to input perturbation. We hypothesize that the high sensitivity to the perturbation of data degrades the performance on it. To reduce the sensitivity to…

Machine Learning · Statistics 2017-06-01 Yuichi Yoshida , Takeru Miyato

Deep neural networks are easily fooled by small perturbations known as adversarial attacks. Adversarial Training (AT) is a technique aimed at learning features robust to such attacks and is widely regarded as a very effective defense.…

Machine Learning · Computer Science 2020-09-11 Theodoros Tsiligkaridis , Jay Roberts

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

Continual Learning addresses the challenge of learning a number of different tasks sequentially. The goal of maintaining knowledge of earlier tasks without re-accessing them starkly conflicts with standard SGD training for artificial neural…

Machine Learning · Computer Science 2021-02-05 Frederik Benzing

While there are many studies on weight regularization, the study on structure regularization is rare. Many existing systems on structured prediction focus on increasing the level of structural dependencies within the model. However, this…

Machine Learning · Computer Science 2015-02-02 Xu Sun

We propose automatic optimisation methods considering the geometry of matrix manifold for the normalised parameters of neural networks. Layerwise weight normalisation with respect to Frobenius norm is utilised to bound the Lipschitz…

Machine Learning · Computer Science 2023-12-19 Namhoon Cho , Hyo-Sang Shin

Recent works have shown that on sufficiently over-parametrized neural nets, gradient descent with relatively large initialization optimizes a prediction function in the RKHS of the Neural Tangent Kernel (NTK). This analysis leads to global…

Machine Learning · Statistics 2020-04-28 Colin Wei , Jason D. Lee , Qiang Liu , Tengyu Ma

Neural networks are more expressive when they have multiple layers. In turn, conventional training methods are only successful if the depth does not lead to numerical issues such as exploding or vanishing gradients, which occur less…

Machine Learning · Computer Science 2022-06-07 Carles Riera , Camilo Rey , Thiago Serra , Eloi Puertas , Oriol Pujol

Normalization layers (e.g., Batch Normalization, Layer Normalization) were introduced to help with optimization difficulties in very deep nets, but they clearly also help generalization, even in not-so-deep nets. Motivated by the long-held…

Machine Learning · Computer Science 2023-01-18 Kaifeng Lyu , Zhiyuan Li , Sanjeev Arora

First-order stochastic optimization methods are currently the most widely used class of methods for training deep neural networks. However, the choice of the optimizer has become an ad-hoc rule that can significantly affect the performance.…

Machine Learning · Computer Science 2020-10-21 Samy Jelassi , Aaron Defazio

The key to generalization is controlling the complexity of the network. However, there is no obvious control of complexity -- such as an explicit regularization term -- in the training of deep networks for classification. We will show that…

Machine Learning · Computer Science 2020-04-14 Andrzej Banburski , Qianli Liao , Brando Miranda , Lorenzo Rosasco , Fernanda De La Torre , Jack Hidary , Tomaso Poggio