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
Posted Content
Advances and Open Problems in Federated Learning
Peter Kairouz,H. Brendan McMahan,Brendan Avent,Aurélien Bellet,Mehdi Bennis,Arjun Nitin Bhagoji,Kallista Bonawitz,Zachary Charles,Graham Cormode,Rachel Cummings,Rafael G. L. D'Oliveira,Hubert Eichner,Salim El Rouayheb,David Evans,Josh Gardner,Zachary Garrett,Adrià Gascón,Badih Ghazi,Phillip B. Gibbons,Marco Gruteser,Zaid Harchaoui,Chaoyang He,Lie He,Zhouyuan Huo,Ben Hutchinson,Justin Hsu,Martin Jaggi,Tara Javidi,Gauri Joshi,Mikhail Khodak,Jakub Konečný,Aleksandra Korolova,Farinaz Koushanfar,Sanmi Koyejo,Tancrède Lepoint,Yang Liu,Prateek Mittal,Mehryar Mohri,Richard Nock,Ayfer Ozgur,Rasmus Pagh,Mariana Raykova,Hang Qi,Daniel Ramage,Ramesh Raskar,Dawn Song,Weikang Song,Sebastian U. Stich,Ziteng Sun,Ananda Theertha Suresh,Florian Tramèr,Praneeth Vepakomma,Jianyu Wang,Li Xiong,Zheng Xu,Qiang Yang,Felix X. Yu,Han Yu,Sen Zhao +58 more
TL;DR: Motivated by the explosive growth in FL research, this paper discusses recent advances and presents an extensive collection of open problems and challenges.
Posted Content
Rethinking the Value of Network Pruning
TL;DR: It is found that with optimal learning rate, the "winning ticket" initialization as used in Frankle & Carbin (2019) does not bring improvement over random initialization, and the need for more careful baseline evaluations in future research on structured pruning methods is suggested.
Proceedings ArticleDOI
Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned
TL;DR: It is found that the most important and confident heads play consistent and often linguistically-interpretable roles and when pruning heads using a method based on stochastic gates and a differentiable relaxation of the L0 penalty, it is observed that specialized heads are last to be pruned.
Posted Content
Efficient Neural Audio Synthesis
Nal Kalchbrenner,Erich Elsen,Karen Simonyan,Seb Noury,Norman Casagrande,Edward Lockhart,Florian Stimberg,Aaron van den Oord,Sander Dieleman,Koray Kavukcuoglu +9 more
TL;DR: A single-layer recurrent neural network with a dual softmax layer that matches the quality of the state-of-the-art WaveNet model, the WaveRNN, and a new generation scheme based on subscaling that folds a long sequence into a batch of shorter sequences and allows one to generate multiple samples at once.
Journal ArticleDOI
Model Compression and Hardware Acceleration for Neural Networks: A Comprehensive Survey
TL;DR: This article reviews the mainstream compression approaches such as compact model, tensor decomposition, data quantization, and network sparsification, and answers the question of how to leverage these methods in the design of neural network accelerators and present the state-of-the-art hardware architectures.
References
More filters
Posted Content
Compression of Neural Machine Translation Models via Pruning
TL;DR: This paper proposed three simple magnitude-based pruning schemes to compress NMT models, namely class-blind, class-uniform, and class-distribution, which differ in terms of how pruning thresholds are computed for the different classes of weights in the NMT architecture.