English
Related papers

Related papers: Efficient Sparse Training with Structured Dropout

200 papers

In order to develop complex relationships between their inputs and outputs, deep neural networks train and adjust large number of parameters. To make these networks work at high accuracy, vast amounts of data are needed. Sometimes, however,…

Machine Learning · Computer Science 2022-01-19 Joshua Shunk

Sparse training is a natural idea to accelerate the training speed of deep neural networks and save the memory usage, especially since large modern neural networks are significantly over-parameterized. However, most of the existing methods…

Machine Learning · Computer Science 2021-11-11 Xiao Zhou , Weizhong Zhang , Zonghao Chen , Shizhe Diao , Tong Zhang

Overfitting is a major problem in training machine learning models, specifically deep neural networks. This problem may be caused by imbalanced datasets and initialization of the model parameters, which conforms the model too closely to the…

Neural and Evolutionary Computing · Computer Science 2019-02-26 Hojjat Salehinejad , Shahrokh Valaee

Overparameterized transformer networks have obtained state of the art results in various natural language processing tasks, such as machine translation, language modeling, and question answering. These models contain hundreds of millions of…

Machine Learning · Computer Science 2019-09-26 Angela Fan , Edouard Grave , Armand Joulin

This paper proposes a hardware-oriented dropout algorithm, which is efficient for field programmable gate array (FPGA) implementation. In deep neural networks (DNNs), overfitting occurs when networks are overtrained and adapt too well to…

Machine Learning · Computer Science 2019-11-15 Yoeng Jye Yeoh , Takashi Morie , Hakaru Tamukoh

In classification applications, we often want probabilistic predictions to reflect confidence or uncertainty. Dropout, a commonly used training technique, has recently been linked to Bayesian inference, yielding an efficient way to quantify…

Machine Learning · Computer Science 2019-06-25 Zhilu Zhang , Adrian V. Dalca , Mert R. Sabuncu

Deep neural networks are typically trained by uniformly sampling large datasets across epochs, despite evidence that not all samples contribute equally throughout learning. Recent work shows that progressively reducing the amount of…

Machine Learning · Computer Science 2026-04-15 Amar Gahir , Varshil Patel , Shreyank N Gowda

Regularizers help deep neural networks prevent feature co-adaptations. Dropout, as a commonly used regularization technique, stochastically disables neuron activations during network optimization. However, such complete feature disposal can…

Machine Learning · Computer Science 2022-01-25 Tiange Xiang , Chaoyi Zhang , Yang Song , Siqi Liu , Hongliang Yuan , Weidong Cai

Dropout and its extensions (eg. DropBlock and DropConnect) are popular heuristics for training neural networks, which have been shown to improve generalization performance in practice. However, a theoretical understanding of their…

Machine Learning · Computer Science 2020-06-23 Ambar Pal , Connor Lane , René Vidal , Benjamin D. Haeffele

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

Conventional training of deep neural networks usually requires a substantial amount of data with expensive human annotations. In this paper, we utilize the idea of meta-learning to explain two very different streams of few-shot learning,…

Computer Vision and Pattern Recognition · Computer Science 2022-10-13 Shaobo Lin , Xingyu Zeng , Rui Zhao

Deep learning models frequently exploit spurious features in training data to achieve low training error, often resulting in poor generalization when faced with shifted testing distributions. To address this issue, various methods from…

Machine Learning · Computer Science 2025-02-11 Geraldin Nanfack , Eugene Belilovsky

A standard hardware bottleneck when training deep neural networks is GPU memory. The bulk of memory is occupied by caching intermediate tensors for gradient computation in the backward pass. We propose a novel method to reduce this…

Computer Vision and Pattern Recognition · Computer Science 2023-03-03 Joya Chen , Kai Xu , Yuhui Wang , Yifei Cheng , Angela Yao

We introduce a dynamic sparse training algorithm based on linearized Bregman iterations / mirror descent that exploits the naturally incurred sparsity by alternating between periods of static and dynamic sparsity pattern updates. The key…

Machine Learning · Computer Science 2026-05-19 Yannick Lunk , Sebastian J. Scott , Leon Bungert

Pretrained language models have achieved remarkable success in natural language understanding. However, fine-tuning pretrained models on limited training data tends to overfit and thus diminish performance. This paper presents Bi-Drop, a…

Computation and Language · Computer Science 2023-10-24 Shoujie Tong , Heming Xia , Damai Dai , Runxin Xu , Tianyu Liu , Binghuai Lin , Yunbo Cao , Zhifang Sui

It is generally perceived that Dynamic Sparse Training opens the door to a new era of scalability and efficiency for artificial neural networks at, perhaps, some costs in accuracy performance for the classification task. At the same time,…

Computer Vision and Pattern Recognition · Computer Science 2025-03-06 Boqian Wu , Qiao Xiao , Shunxin Wang , Nicola Strisciuglio , Mykola Pechenizkiy , Maurice van Keulen , Decebal Constantin Mocanu , Elena Mocanu

In the last decade, exponential data growth supplied the machine learning-based algorithms' capacity and enabled their usage in daily life activities. Additionally, such an improvement is partially explained due to the advent of deep…

Machine Learning · Computer Science 2022-03-08 Claudio Filipi Goncalves do Santos , Mateus Roder , Leandro A. Passos , João P. Papa

Federated learning (FL) is a popular framework for training an AI model using distributed mobile data in a wireless network. It features data parallelism by distributing the learning task to multiple edge devices while attempting to…

Machine Learning · Computer Science 2022-02-08 Dingzhu Wen , Ki-Jun Jeon , Kaibin Huang

Deep neural networks with their large number of parameters are highly flexible learning systems. The high flexibility in such networks brings with some serious problems such as overfitting, and regularization is used to address this…

Machine Learning · Statistics 2017-12-20 Beyza Ermis , Ali Taylan Cemgil

Improvements in the performance of deep neural networks have often come through the design of larger and more complex networks. As a result, fast memory is a significant limiting factor in our ability to improve network performance. One…

Machine Learning · Computer Science 2019-12-25 Simon Alford , Ryan Robinett , Lauren Milechin , Jeremy Kepner
‹ Prev 1 3 4 5 6 7 10 Next ›