English
Related papers

Related papers: The Expressive Power of Tuning Only the Normalizat…

200 papers

In spite of finite dimension ReLU neural networks being a consistent factor behind recent deep learning successes, a theory of feature learning in these models remains elusive. Currently, insightful theories still rely on assumptions…

Machine Learning · Computer Science 2025-04-01 Devon Jarvis , Richard Klein , Benjamin Rosman , Andrew M. Saxe

We introduce and analyze a new technique for model reduction for deep neural networks. While large networks are theoretically capable of learning arbitrarily complex models, overfitting and model redundancy negatively affects the prediction…

Machine Learning · Computer Science 2017-11-27 Alireza Aghasi , Afshin Abdi , Nam Nguyen , Justin Romberg

We propose and analyze a new family of algorithms for training neural networks with ReLU activations. Our algorithms are based on the technique of alternating minimization: estimating the activation patterns of each ReLU for all given…

Machine Learning · Computer Science 2018-10-12 Gauri Jagatap , Chinmay Hegde

Understanding deep neural networks is a major research objective with notable experimental and theoretical attention in recent years. The practical success of excessively large networks underscores the need for better theoretical analyses…

Machine Learning · Statistics 2022-03-10 Chiyuan Zhang , Samy Bengio , Yoram Singer

Deep Neural Networks have achieved remarkable success relying on the developing high computation capability of GPUs and large-scale datasets with increasing network depth and width in image recognition, object detection and many other…

Machine Learning · Computer Science 2020-01-08 E Zhenqian , Gao Weiguo

Effectively scaling up deep reinforcement learning models has proven notoriously difficult due to network pathologies during training, motivating various targeted interventions such as periodic reset and architectural advances such as layer…

Machine Learning · Computer Science 2025-06-23 Guozheng Ma , Lu Li , Zilin Wang , Li Shen , Pierre-Luc Bacon , Dacheng Tao

Equivariant neural networks have shown improved performance, expressiveness and sample complexity on symmetrical domains. But for some specific symmetries, representations, and choice of coordinates, the most common point-wise activations,…

Machine Learning · Computer Science 2024-01-18 Marco Pacini , Xiaowen Dong , Bruno Lepri , Gabriele Santin

Recent work in the literature has shown experimentally that one can use the lower layers of a trained convolutional neural network (CNN) to model natural textures. More interestingly, it has also been experimentally shown that only one…

Computer Vision and Pattern Recognition · Computer Science 2016-12-20 Mihir Mongia , Kundan Kumar , Akram Erraqabi , Yoshua Bengio

Feature representations from pre-trained deep neural networks have been known to exhibit excellent generalization and utility across a variety of related tasks. Fine-tuning is by far the simplest and most widely used approach that seeks to…

Computer Vision and Pattern Recognition · Computer Science 2017-10-09 Donghyun Yoo , Haoqi Fan , Vishnu Naresh Boddeti , Kris M. Kitani

Online Normalization is a new technique for normalizing the hidden activations of a neural network. Like Batch Normalization, it normalizes the sample dimension. While Online Normalization does not use batches, it is as accurate as Batch…

State-of-the-art performance on language understanding tasks is now achieved with increasingly large networks; the current record holder has billions of parameters. Given a language model pre-trained on massive unlabeled text corpora, only…

Computation and Language · Computer Science 2020-04-30 Evani Radiya-Dixit , Xin Wang

Training neural networks is an optimization problem, and finding a decent set of parameters through gradient descent can be a difficult task. A host of techniques has been developed to aid this process before and during the training phase.…

Machine Learning · Computer Science 2020-08-19 Divya Gaur , Joachim Folz , Andreas Dengel

Batch Normalization is a key component in almost all state-of-the-art image classifiers, but it also introduces practical challenges: it breaks the independence between training examples within a batch, can incur compute and memory…

Machine Learning · Computer Science 2021-01-28 Andrew Brock , Soham De , Samuel L. Smith

Recent pretrained language models extend from millions to billions of parameters. Thus the need to fine-tune an extremely large pretrained model with a limited training corpus arises in various downstream tasks. In this paper, we propose a…

Computation and Language · Computer Science 2021-09-14 Runxin Xu , Fuli Luo , Zhiyuan Zhang , Chuanqi Tan , Baobao Chang , Songfang Huang , Fei Huang

Neural networks have been shown to improve performance across a range of natural-language tasks. However, designing and training them can be complicated. Frequently, researchers resort to repeated experimentation to pick optimal settings.…

Computation and Language · Computer Science 2015-08-21 Kenton Murray , David Chiang

A popular method to reduce the training time of deep neural networks is to normalize activations at each layer. Although various normalization schemes have been proposed, they all follow a common theme: normalize across spatial dimensions…

Computer Vision and Pattern Recognition · Computer Science 2019-12-20 Boyi Li , Felix Wu , Kilian Q. Weinberger , Serge Belongie

Overparametrized neural networks trained by gradient descent (GD) can provably overfit any training data. However, the generalization guarantee may not hold for noisy data. From a nonparametric perspective, this paper studies how well…

Machine Learning · Statistics 2021-09-28 Tianyang Hu , Wenjia Wang , Cong Lin , Guang Cheng

Deep neural network is difficult to train and this predicament becomes worse as the depth increases. The essence of this problem exists in the magnitude of backpropagated errors that will result in gradient vanishing or exploding…

Computer Vision and Pattern Recognition · Computer Science 2017-04-11 Di Xie , Jiang Xiong , Shiliang Pu

Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. This slows down the training by requiring lower learning rates…

Machine Learning · Computer Science 2015-03-03 Sergey Ioffe , Christian Szegedy

For most state-of-the-art architectures, Rectified Linear Unit (ReLU) becomes a standard component accompanied with each layer. Although ReLU can ease the network training to an extent, the character of blocking negative values may suppress…

Computer Vision and Pattern Recognition · Computer Science 2017-11-20 Xuanyi Dong , Guoliang Kang , Kun Zhan , Yi Yang
‹ Prev 1 3 4 5 6 7 10 Next ›