English
Related papers

Related papers: FreezeOut: Accelerate Training by Progressively Fr…

200 papers

Over the last few years, Deep Neural Networks (DNNs) have become ubiquitous owing to their high accuracy on real-world tasks. However, this increase in accuracy comes at the cost of computationally expensive models leading to higher…

Machine Learning · Computer Science 2020-02-10 Adarsh Kumar , Arjun Balasubramanian , Shivaram Venkataraman , Aditya Akella

Deep neural networks have long training and processing times. Early exits added to neural networks allow the network to make early predictions using intermediate activations in the network in time-sensitive applications. However, early…

Machine Learning · Computer Science 2022-12-27 Devdhar Patel , Hava Siegelmann

Deep neural networks provide state-of-the-art accuracy for vision tasks but they require significant resources for training. Thus, they are trained on cloud servers far from the edge devices that acquire the data. This issue increases…

Computer Vision and Pattern Recognition · Computer Science 2024-05-22 Yamin Sepehri , Pedram Pad , Ahmet Caner Yüzügüler , Pascal Frossard , L. Andrea Dunbar

With the growing size of deep neural networks and datasets, the computational costs of training have significantly increased. The layer-freezing technique has recently attracted great attention as a promising method to effectively reduce…

Machine Learning · Computer Science 2025-08-22 Chence Yang , Ci Zhang , Lei Lu , Qitao Tan , Sheng Li , Ao Li , Xulong Tang , Shaoyi Huang , Jinzhen Wang , Guoming Li , Jundong Li , Xiaoming Zhai , Jin Lu , Geng Yuan

Pushing forward the compute efficacy frontier in deep learning is critical for tasks that require frequent model re-training or workloads that entail training a large number of models. We introduce SliceOut -- a dropout-inspired scheme…

Machine Learning · Computer Science 2021-04-02 Pascal Notin , Aidan N. Gomez , Joanna Yoo , Yarin Gal

This paper proposes a new method to improve the training efficiency of deep convolutional neural networks. During training, the method evaluates scores to measure how much each layer's parameters change and whether the layer will continue…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Giorgio Cruciata , Luca Cruciata , Liliana Lo Presti , Jan Van Gemert , Marco La Cascia

Neural networks offer high-accuracy solutions to a range of problems, but are costly to run in production systems because of computational and memory requirements during a forward pass. Given a trained network, we propose a techique called…

Computer Vision and Pattern Recognition · Computer Science 2018-06-18 Michele Pratusevich

Recently, sparse training has emerged as a promising paradigm for efficient deep learning on edge devices. The current research mainly devotes efforts to reducing training costs by further increasing model sparsity. However, increasing…

Machine Learning · Computer Science 2022-09-23 Geng Yuan , Yanyu Li , Sheng Li , Zhenglun Kong , Sergey Tulyakov , Xulong Tang , Yanzhi Wang , Jian Ren

Pruning generates sparse networks by setting parameters to zero. In this work we improve one-shot pruning methods, applied before training, without adding any additional storage costs while preserving the sparse gradient computations. The…

Machine Learning · Computer Science 2022-03-17 Paul Wimmer , Jens Mehnert , Alexandru Condurache

Training deep Convolutional Neural Networks (CNN) is a time consuming task that may take weeks to complete. In this article we propose a novel, theoretically founded method for reducing CNN training time without incurring any loss in…

Computer Vision and Pattern Recognition · Computer Science 2016-10-13 Pedro Porto Buarque de Gusmão , Gianluca Francini , Skjalg Lepsøy , Enrico Magli

Training deep convolutional neural networks such as VGG and ResNet by gradient descent is an expensive exercise requiring specialized hardware such as GPUs. Recent works have examined the possibility of approximating the gradient…

Computer Vision and Pattern Recognition · Computer Science 2019-08-16 Ziheng Wang , Sree Harsha Nelaturu

Tensor decomposition is one of the well-known approaches to reduce the latency time and number of parameters of a pre-trained model. However, in this paper, we propose an approach to use tensor decomposition to reduce training time of…

Computer Vision and Pattern Recognition · Computer Science 2020-06-30 Mostafa Elhoushi , Ye Henry Tian , Zihao Chen , Farhan Shafiq , Joey Yiwei Li

With the rapid adoption of machine learning (ML), a number of domains now use the approach of fine tuning models which were pre-trained on a large corpus of data. However, our experiments show that even fine-tuning on models like BERT can…

Machine Learning · Computer Science 2021-04-06 Yuhan Liu , Saurabh Agarwal , Shivaram Venkataraman

Training deep neural networks (DNNs) is time-consuming. While most existing solutions try to overlap/schedule computation and communication for efficient training, this paper goes one step further by skipping computing and communication…

Machine Learning · Computer Science 2023-03-14 Yiding Wang , Decang Sun , Kai Chen , Fan Lai , Mosharaf Chowdhury

For deploying a deep learning model into production, it needs to be both accurate and compact to meet the latency and memory constraints. This usually results in a network that is deep (to ensure performance) and yet thin (to improve…

Machine Learning · Computer Science 2020-08-18 Denny Zhou , Mao Ye , Chen Chen , Tianjian Meng , Mingxing Tan , Xiaodan Song , Quoc Le , Qiang Liu , Dale Schuurmans

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

The increasing complexity of deep learning architectures is resulting in training time requiring weeks or even months. This slow training is due in part to vanishing gradients, in which the gradients used by back-propagation are extremely…

Computer Vision and Pattern Recognition · Computer Science 2015-10-16 Bharat Singh , Soham De , Yangmuzi Zhang , Thomas Goldstein , Gavin Taylor

Fully-connected layers in deep neural networks (DNN) are often the throughput and power bottleneck during training. This is due to their large size and low data reuse. Pruning dense layers can significantly reduce the size of these…

Machine Learning · Computer Science 2018-02-13 Mihailo Isakov , Michel A. Kinsy

Compression of a neural network can help in speeding up both the training and the inference of the network. In this research, we study applying compression using low rank decomposition on network layers. Our research demonstrates that to…

Computer Vision and Pattern Recognition · Computer Science 2023-09-25 Walid Ahmed , Habib Hajimolahoseini , Austin Wen , Yang Liu

Federated learning is used for decentralized training of machine learning models on a large number (millions) of edge mobile devices. It is challenging because mobile devices often have limited communication bandwidth and local computation…

Machine Learning · Computer Science 2021-11-09 Hakim Sidahmed , Zheng Xu , Ankush Garg , Yuan Cao , Mingqing Chen
‹ Prev 1 2 3 10 Next ›