English
Related papers

Related papers: Fixup Initialization: Residual Learning Without No…

200 papers

Despite their widespread use, training deep Transformers can be unstable. Layer normalization, a standard component, improves training stability, but its placement has often been ad-hoc. In this paper, we conduct a principled study on the…

Machine Learning · Computer Science 2025-10-14 Kelvin Kan , Xingjian Li , Benjamin J. Zhang , Tuhin Sahai , Stanley Osher , Krishna Kumar , Markos A. Katsoulakis

We present a general framework for training deep neural networks without backpropagation. This substantially decreases training time and also allows for construction of deep networks with many sorts of learners, including networks whose…

Machine Learning · Statistics 2017-06-09 Chris Hettinger , Tanner Christensen , Ben Ehlert , Jeffrey Humpherys , Tyler Jarvis , Sean Wade

Batch Normalization (BN) is widely used in {centralized} deep learning to improve convergence and generalization. However, in {federated} learning (FL) with decentralized data, prior work has observed that training with BN could hinder…

Machine Learning · Computer Science 2024-04-01 Jike Zhong , Hong-You Chen , Wei-Lun Chao

Traditional end-to-end deep learning models often enhance feature representation and overall performance by increasing the depth and complexity of the network during training. However, this approach inevitably introduces issues of parameter…

Computer Vision and Pattern Recognition · Computer Science 2024-10-03 Yuming Zhang , Peizhe Wang , Shouxin Zhang , Dongzhi Guan , Jiabin Liu , Junhao Su

In supervised learning, the regularization path is sometimes used as a convenient theoretical proxy for the optimization path of gradient descent initialized from zero. In this paper, we study a modification of the regularization path for…

Machine Learning · Computer Science 2023-08-10 Sebastian Neumayer , Lénaïc Chizat , Michael Unser

Convolution neural networks have achieved remarkable performance in many tasks of computing vision. However, CNN tends to bias to low frequency components. They prioritize capturing low frequency patterns which lead them fail when suffering…

Machine Learning · Computer Science 2020-07-08 Weiyu Guo , Yidong Ouyang

Mixup is a popular regularization technique for training deep neural networks that improves generalization and increases robustness to certain distribution shifts. It perturbs input training data in the direction of other randomly-chosen…

Machine Learning · Computer Science 2023-10-10 Kristjan Greenewald , Anming Gu , Mikhail Yurochkin , Justin Solomon , Edward Chien

The proper initialization of weights is crucial for the effective training and fast convergence of deep neural networks (DNNs). Prior work in this area has mostly focused on balancing the variance among weights per layer to maintain…

Machine Learning · Computer Science 2020-06-05 Maciej Skorski , Alessandro Temperoni , Martin Theobald

We propose a regularization scheme for image reconstruction that leverages the power of deep learning while hinging on classic sparsity-promoting models. Many deep-learning-based models are hard to interpret and cumbersome to analyze…

Image and Video Processing · Electrical Eng. & Systems 2024-07-10 Mehrsa Pourya , Sebastian Neumayer , Michael Unser

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

Convolutional neural networks (CNNs) often perform well, but their stability is poorly understood. To address this problem, we consider the simple prototypical problem of signal denoising, where classical approaches such as nonlinear…

Machine Learning · Computer Science 2020-06-09 Tobias Alt , Joachim Weickert , Pascal Peter

Training deep neural networks is known to require a large number of training samples. However, in many applications only few training samples are available. In this work, we tackle the issue of training neural networks for classification…

Machine Learning · Computer Science 2017-12-25 Soufiane Belharbi , Clément Chatelain , Romain Hérault , Sébastien Adam

It is important to understand how dropout, a popular regularization method, aids in achieving a good generalization solution during neural network training. In this work, we present a theoretical derivation of an implicit regularization of…

Machine Learning · Computer Science 2023-04-11 Zhongwang Zhang , Zhi-Qin John Xu

MixUp is a recently proposed data-augmentation scheme, which linearly interpolates a random pair of training examples and correspondingly the one-hot representations of their labels. Training deep neural networks with such additional data…

Machine Learning · Computer Science 2018-11-26 Hongyu Guo , Yongyi Mao , Richong Zhang

Initializing the weights and the biases is a key part of the training process of a neural network. Unlike the subsequent optimization phase, however, the initialization phase has gained only limited attention in the literature. In this…

Machine Learning · Computer Science 2019-09-06 Ingo Steinwart

Fourier phase retrieval is a classical problem of restoring a signal only from the measured magnitude of its Fourier transform. Although Fienup-type algorithms, which use prior knowledge in both spatial and Fourier domains, have been widely…

Computer Vision and Pattern Recognition · Computer Science 2020-11-23 Eunju Cha , Chanseok Lee , Mooseok Jang , Jong Chul Ye

While variational methods have been among the most powerful tools for solving linear inverse problems in imaging, deep (convolutional) neural networks have recently taken the lead in many challenging benchmarks. A remaining drawback of deep…

Computer Vision and Pattern Recognition · Computer Science 2019-08-20 Tim Meinhardt , Michael Moeller , Caner Hazirbas , Daniel Cremers

Blind Super-Resolution (blind SR) aims to enhance the model's generalization ability with unknown degradation, yet it still encounters severe overfitting issues. Some previous methods inspired by dropout, which enhances generalization by…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Hang Xu , Wei Yu , Jiangtong Tan , Zhen Zou , Feng Zhao

Very deep convolutional neural networks introduced new problems like vanishing gradient and degradation. The recent successful contributions towards solving these problems are Residual and Highway Networks. These networks introduce skip…

Computer Vision and Pattern Recognition · Computer Science 2016-10-06 Anish Shah , Eashan Kadam , Hena Shah , Sameer Shinde , Sandip Shingade

A core issue with learning to optimize neural networks has been the lack of generalization to real world problems. To address this, we describe a system designed from a generalization-first perspective, learning to update optimizer…

Machine Learning · Computer Science 2021-06-09 Diogo Almeida , Clemens Winter , Jie Tang , Wojciech Zaremba