Open AccessPosted Content
To prune, or not to prune: exploring the efficacy of pruning for model compression
Michael H. Zhu,Suyog Gupta +1 more
Reads0
Chats0
TLDR
In this article, the authors investigate two distinct paths for model compression within the context of energy-efficient inference in resource-constrained environments and propose a new gradual pruning technique that is simple and straightforward to apply across a variety of models/datasets with minimal tuning.Abstract:
Model pruning seeks to induce sparsity in a deep neural network's various connection matrices, thereby reducing the number of nonzero-valued parameters in the model. Recent reports (Han et al., 2015; Narang et al., 2017) prune deep networks at the cost of only a marginal loss in accuracy and achieve a sizable reduction in model size. This hints at the possibility that the baseline models in these experiments are perhaps severely over-parameterized at the outset and a viable alternative for model compression might be to simply reduce the number of hidden units while maintaining the model's dense connection structure, exposing a similar trade-off in model size and accuracy. We investigate these two distinct paths for model compression within the context of energy-efficient inference in resource-constrained environments and propose a new gradual pruning technique that is simple and straightforward to apply across a variety of models/datasets with minimal tuning and can be seamlessly incorporated within the training process. We compare the accuracy of large, but pruned models (large-sparse) and their smaller, but dense (small-dense) counterparts with identical memory footprint. Across a broad range of neural network architectures (deep CNNs, stacked LSTM, and seq2seq LSTM models), we find large-sparse models to consistently outperform small-dense models and achieve up to 10x reduction in number of non-zero parameters with minimal loss in accuracy.read more
Citations
More filters
Proceedings ArticleDOI
Pruned and Structurally Sparse Neural Networks
TL;DR: Results show that compared to dense topologies, sparse structures show promise in training potential but also can exhibit highly nonlinear convergence, which merits further study.
Proceedings ArticleDOI
Overcoming Oscillations in Quantization-Aware Training
TL;DR: The phenomenon of weight oscillations can lead to a significant accuracy degradation due to wrongly estimated batch-normalization statistics during inference and increased noise during training, and two novel QAT algorithms are proposed to overcome oscillations during training.
Proceedings ArticleDOI
EdgeL^3: Compressing L^3-Net for Mote Scale Urban Noise Monitoring
TL;DR: This paper uses pruning, ablation, and knowledge distillation techniques to show that the originally proposed L3-Net architecture is substantially overparameterized, not only for AVC but for the target task of sound classification as evaluated on two popular downstream datasets.
Proceedings ArticleDOI
Characterizing Sources of Ineffectual Computations in Deep Learning Networks
TL;DR: It is demonstrated that such properties persist in more recent and thus more accurate and better performing image classification networks, models for image applications other than classification such as image segmentation and low-level computational imaging, and Long-Short-Term-Memory models for non-image applications such as those for natural language processing.
Posted Content
Fully Quantized Transformer for Machine Translation.
TL;DR: This work is the first to show that it is possible to avoid any loss in translation quality with a fully quantized Transformer, and compared to full-precision, their 8-bit models score greater or equal BLEU on most tasks.
References
More filters
Posted Content
Rethinking the Inception Architecture for Computer Vision
TL;DR: This work is exploring ways to scale up networks in ways that aim at utilizing the added computation as efficiently as possible by suitably factorized convolutions and aggressive regularization.
Posted Content
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Andrew Howard,Menglong Zhu,Bo Chen,Dmitry Kalenichenko,Weijun Wang,Tobias Weyand,M. Andreetto,Hartwig Adam +7 more
TL;DR: This work introduces two simple global hyper-parameters that efficiently trade off between latency and accuracy and demonstrates the effectiveness of MobileNets across a wide range of applications and use cases including object detection, finegrain classification, face attributes and large scale geo-localization.
Proceedings Article
Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
TL;DR: Deep Compression as mentioned in this paper proposes a three-stage pipeline: pruning, quantization, and Huffman coding to reduce the storage requirement of neural networks by 35x to 49x without affecting their accuracy.
Posted Content
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
Yonghui Wu,Mike Schuster,Zhifeng Chen,Quoc V. Le,Mohammad Norouzi,Wolfgang Macherey,Maxim Krikun,Yuan Cao,Qin Gao,Klaus Macherey,Jeff Klingner,Apurva Shah,Melvin Johnson,Xiaobing Liu,Łukasz Kaiser,Stephan Gouws,Yoshikiyo Kato,Taku Kudo,Hideto Kazawa,Keith Stevens,George Kurian,Nishant Patil,Wei Wang,Cliff Young,Jason A. Smith,Jason Riesa,Alex Rudnick,Oriol Vinyals,Greg S. Corrado,Macduff Hughes,Jeffrey Dean +30 more
TL;DR: GNMT, Google's Neural Machine Translation system, is presented, which attempts to address many of the weaknesses of conventional phrase-based translation systems and provides a good balance between the flexibility of "character"-delimited models and the efficiency of "word"-delicited models.
Proceedings Article
Learning both weights and connections for efficient neural networks
TL;DR: In this paper, the authors proposed a method to reduce the storage and computation required by neural networks by an order of magnitude without affecting their accuracy by learning only the important connections using a three-step method.