English
Related papers

Related papers: Highly Scalable Deep Learning Training System with…

200 papers

There has been a strong demand for algorithms that can execute machine learning as faster as possible and the speed of deep learning has accelerated by 30 times only in the past two years. Distributed deep learning using the large…

Deep learning thrives with large neural networks and large datasets. However, larger networks and larger datasets result in longer training times that impede research and development progress. Distributed synchronous SGD offers a potential…

Computer Vision and Pattern Recognition · Computer Science 2018-05-02 Priya Goyal , Piotr Dollár , Ross Girshick , Pieter Noordhuis , Lukasz Wesolowski , Aapo Kyrola , Andrew Tulloch , Yangqing Jia , Kaiming He

The speed of deep neural networks training has become a big bottleneck of deep learning research and development. For example, training GoogleNet by ImageNet dataset on one Nvidia K20 GPU needs 21 days. To speed up the training process, the…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-08-11 Yang You , Aydin Buluc , James Demmel

Scaling the distributed deep learning to a massive GPU cluster level is challenging due to the instability of the large mini-batch training and the overhead of the gradient synchronization. We address the instability of the large mini-batch…

Machine Learning · Computer Science 2019-03-06 Hiroaki Mikami , Hisahiro Suganuma , Pongsakorn U-chupala , Yoshiki Tanaka , Yuichi Kageyama

Deep learning has led to tremendous advancements in the field of Artificial Intelligence. One caveat however is the substantial amount of compute needed to train these deep learning models. Training a benchmark dataset like ImageNet on a…

Machine Learning · Computer Science 2018-10-30 Karanbir Chahal , Manraj Singh Grover , Kuntal Dey

For the past 5 years, the ILSVRC competition and the ImageNet dataset have attracted a lot of interest from the Computer Vision community, allowing for state-of-the-art accuracy to grow tremendously. This should be credited to the use of…

Machine Learning · Statistics 2017-11-17 Valeriu Codreanu , Damian Podareanu , Vikram Saletore

Distributed training techniques have been widely deployed in large-scale deep neural networks (DNNs) training on dense-GPU clusters. However, on public cloud clusters, due to the moderate inter-connection bandwidth between instances,…

It is important to scale out deep neural network (DNN) training for reducing model training time. The high communication overhead is one of the major performance bottlenecks for distributed DNN training across multiple GPUs. Our…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-10-23 Peng Sun , Wansen Feng , Ruobing Han , Shengen Yan , Yonggang Wen

We demonstrate that training ResNet-50 on ImageNet for 90 epochs can be achieved in 15 minutes with 1024 Tesla P100 GPUs. This was made possible by using a large minibatch size of 32k. To maintain accuracy with this large minibatch size, we…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-11-15 Takuya Akiba , Shuji Suzuki , Keisuke Fukuda

Deep Neural Networks (DNNs) have achieved im- pressive accuracy in many application domains including im- age classification. Training of DNNs is an extremely compute- intensive process and is solved using variants of the stochastic…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-11-03 Sameer Kumar , Dheeraj Sreedhar , Vaibhav Saxena , Yogish Sabharwal , Ashish Verma

SGD is the widely adopted method to train CNN. Conceptually it approximates the population with a randomly sampled batch; then it evenly trains batches by conducting a gradient update on every batch in an epoch. In this paper, we…

Machine Learning · Computer Science 2017-03-29 Linnan Wang , Yi Yang , Martin Renqiang Min , Srimat Chakradhar

Finishing 90-epoch ImageNet-1k training with ResNet-50 on a NVIDIA M40 GPU takes 14 days. This training requires 10^18 single precision operations in total. On the other hand, the world's current fastest supercomputer can finish 2 * 10^17…

Computer Vision and Pattern Recognition · Computer Science 2018-02-01 Yang You , Zhao Zhang , Cho-Jui Hsieh , James Demmel , Kurt Keutzer

In this work we propose an accelerated stochastic learning system for very large-scale applications. Acceleration is achieved by mapping the training algorithm onto massively parallel processors: we demonstrate a parallel, asynchronous GPU…

Machine Learning · Computer Science 2017-02-24 Thomas Parnell , Celestine Dünner , Kubilay Atasu , Manolis Sifalakis , Haris Pozidis

Deep learning is extremely computationally intensive, and hardware vendors have responded by building faster accelerators in large clusters. Training deep learning models at petaFLOPS scale requires overcoming both algorithmic and systems…

Machine Learning · Computer Science 2018-12-04 Chris Ying , Sameer Kumar , Dehao Chen , Tao Wang , Youlong Cheng

Large-scale distributed training of deep neural networks results in models with worse generalization performance as a result of the increase in the effective mini-batch size. Previous approaches attempt to address this problem by varying…

Machine Learning · Computer Science 2020-02-17 Kazuki Osawa , Yohei Tsuji , Yuichiro Ueno , Akira Naruse , Chuan-Sheng Foo , Rio Yokota

EfficientNets are a family of state-of-the-art image classification models based on efficiently scaled convolutional neural networks. Currently, EfficientNets can take on the order of days to train; for example, training an EfficientNet-B0…

Machine Learning · Computer Science 2020-11-06 Arissa Wongpanich , Hieu Pham , James Demmel , Mingxing Tan , Quoc Le , Yang You , Sameer Kumar

Modern Automatic Speech Recognition (ASR) systems rely on distributed deep learning to for quick training completion. To enable efficient distributed training, it is imperative that the training algorithms can converge with a large…

Audio and Speech Processing · Electrical Eng. & Systems 2019-07-15 Wei Zhang , Xiaodong Cui , Ulrich Finkler , George Saon , Abdullah Kayi , Alper Buyuktosunoglu , Brian Kingsbury , David Kung , Michael Picheny

Training deep neural networks with Stochastic Gradient Descent, or its variants, requires careful choice of both learning rate and batch size. While smaller batch sizes generally converge in fewer training epochs, larger batch sizes offer…

Machine Learning · Computer Science 2018-02-15 Aditya Devarakonda , Maxim Naumov , Michael Garland

Motivated by extreme multi-label classification applications, we consider training deep learning models over sparse data in multi-GPU servers. The variance in the number of non-zero features across training batches and the intrinsic GPU…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-10-15 Yujing Ma , Florin Rusu , Kesheng Wu , Alexander Sim

A common way to speed up training of large convolutional networks is to add computational units. Training is then performed using data-parallel synchronous Stochastic Gradient Descent (SGD) with mini-batch divided between computational…

Computer Vision and Pattern Recognition · Computer Science 2017-09-15 Yang You , Igor Gitman , Boris Ginsburg
‹ Prev 1 2 3 10 Next ›