English
Related papers

Related papers: Weight Rescaling: Effective and Robust Regularizat…

200 papers

Continual learning entails learning a sequence of tasks and balancing their knowledge appropriately. With limited access to old training samples, much of the current work in deep neural networks has focused on overcoming catastrophic…

Machine Learning · Computer Science 2023-10-16 Yilin Lyu , Liyuan Wang , Xingxing Zhang , Zicheng Sun , Hang Su , Jun Zhu , Liping Jing

Although quantization has emerged as a promising approach to reducing computational complexity across various high-level vision tasks, it inevitably leads to accuracy loss in image super-resolution (SR) networks. This is due to the…

Computer Vision and Pattern Recognition · Computer Science 2024-07-19 Cheeun Hong , Kyoung Mu Lee

Residual networks (ResNets) have displayed impressive results in pattern recognition and, recently, have garnered considerable theoretical interest due to a perceived link with neural ordinary differential equations (neural ODEs). This link…

Machine Learning · Computer Science 2021-06-11 Alain-Sam Cohen , Rama Cont , Alain Rossier , Renyuan Xu

Binary neural networks (BNNs) have received increasing attention due to their superior reductions of computation and memory. Most existing works focus on either lessening the quantization error by minimizing the gap between the…

Machine Learning · Computer Science 2021-08-03 Zihan Xu , Mingbao Lin , Jianzhuang Liu , Jie Chen , Ling Shao , Yue Gao , Yonghong Tian , Rongrong Ji

Proper regularization is critical for speeding up training, improving generalization performance, and learning compact models that are cost efficient. We propose and analyze regularized gradient descent algorithms for learning shallow…

Machine Learning · Computer Science 2018-06-08 Samet Oymak

Exciting new work on the generalization bounds for neural networks (NN) given by Neyshabur et al. , Bartlett et al. closely depend on two parameter-depenedent quantities: the Lipschitz constant upper-bound and the stable rank (a softer…

Machine Learning · Statistics 2020-02-21 Amartya Sanyal , Philip H. S. Torr , Puneet K. Dokania

Learning in Deep Neural Networks (DNN) takes place by minimizing a non-convex high-dimensional loss function, typically by a stochastic gradient descent (SGD) strategy. The learning process is observed to be able to find good minimizers…

Machine Learning · Computer Science 2020-03-12 Carlo Baldassi , Fabrizio Pittorino , Riccardo Zecchina

Multiplicative stochasticity such as Dropout improves the robustness and generalizability of deep neural networks. Here, we further demonstrate that always-on multiplicative stochasticity combined with simple threshold neurons are…

Machine Learning · Computer Science 2019-10-29 Georgios Detorakis , Sourav Dutta , Abhishek Khanna , Matthew Jerry , Suman Datta , Emre Neftci

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

Binary Neural Network (BNN) shows its predominance in reducing the complexity of deep neural networks. However, it suffers severe performance degradation. One of the major impediments is the large quantization error between the…

Computer Vision and Pattern Recognition · Computer Science 2020-10-23 Mingbao Lin , Rongrong Ji , Zihan Xu , Baochang Zhang , Yan Wang , Yongjian Wu , Feiyue Huang , Chia-Wen Lin

Despite their impressive performance, Deep Neural Networks (DNNs) typically underperform Gradient Boosting Trees (GBTs) on many tabular-dataset learning tasks. We propose that applying a different regularization coefficient to each weight…

Machine Learning · Statistics 2018-10-25 Ira Shavitt , Eran Segal

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

This paper proposes a set of new error criteria and learning approaches, Adaptive Normalized Risk-Averting Training (ANRAT), to attack the non-convex optimization problem in training deep neural networks (DNNs). Theoretically, we…

Machine Learning · Computer Science 2016-06-10 Zhiguang Wang , Tim Oates , James Lo

Deep neural networks (DNNs) at convergence consistently represent the training data in the last layer via a highly symmetric geometric structure referred to as neural collapse. This empirical evidence has spurred a line of theoretical…

Machine Learning · Computer Science 2024-10-08 Arthur Jacot , Peter Súkeník , Zihan Wang , Marco Mondelli

During training, the weights of a Deep Neural Network (DNN) are optimized from a random initialization towards a nearly optimum value minimizing a loss function. Only this final state of the weights is typically kept for testing, while the…

Machine Learning · Computer Science 2021-03-26 Gianni Franchi , Andrei Bursuc , Emanuel Aldea , Severine Dubuisson , Isabelle Bloch

The weight matrix (WM) of a neural network (NN) is its program. The programs of many traditional NNs are learned through gradient descent in some error function, then remain fixed. The WM of a self-referential NN, however, can keep rapidly…

Machine Learning · Computer Science 2022-06-20 Kazuki Irie , Imanol Schlag , Róbert Csordás , Jürgen Schmidhuber

Background: Deep learning models are typically trained using stochastic gradient descent or one of its variants. These methods update the weights using their gradient, estimated from a small fraction of the training data. It has been…

Machine Learning · Statistics 2018-01-03 Elad Hoffer , Itay Hubara , Daniel Soudry

The effect of regularizers such as weight decay when training deep neural networks is not well understood. We study the influence of weight decay as well as $L2$-regularization when training neural network models in which parameter matrices…

Machine Learning · Computer Science 2024-11-01 Seijin Kobayashi , Yassir Akram , Johannes Von Oswald

Recurrent Neural Networks (RNNs) are rich models for the processing of sequential data. Recent work on advancing the state of the art has been focused on the optimization or modelling of RNNs, mostly motivated by adressing the problems of…

For many practical computer vision applications, the learned models usually have high performance on the datasets used for training but suffer from significant performance degradation when deployed in new environments, where there are…

Computer Vision and Pattern Recognition · Computer Science 2022-03-14 Xin Jin , Cuiling Lan , Wenjun Zeng , Zhibo Chen