paper-with-me

홈 › Papers

Toward Extremely Low Bit and Lossless Accuracy in DNNs with Progressive ADMM

2019-05-02 · Sheng Lin, Xiaolong Ma, Shaokai Ye, Geng Yuan, Kaisheng Ma, Yanzhi Wang

Weight quantization is one of the most important techniques of Deep Neural Networks (DNNs) model compression method. A recent work using systematic framework of DNN weight quantization with the advanced optimization algorithm ADMM (Alternating Direction Methods of Multipliers) achieves one of state-of-art results in weight quantization. In this work, we first extend such ADMM-based framework to guarantee solution feasibility and we have further developed a multi-step, progressive DNN weight quantization framework, with dual benefits of (i) achieving further weight quantization thanks to the special property of ADMM regularization, and (ii) reducing the search space within each step. Extensive experimental results demonstrate the superior performance compared with prior work. Some highlights: we derive the first lossless and fully binarized (for all layers) LeNet-5 for MNIST; And we derive the first fully binarized (for all layers) VGG-16 for CIFAR-10 and ResNet for ImageNet with reasonable accuracy loss.

📄 PDF Abstract BibTeX arXiv:1905.00789

Code (0)

등록된 구현이 없습니다.

Tasks

Model CompressionQuantization

Methods 이 논문이 사용한 방법론

Average Pooling 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Batch Normalization 설명 없음
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…
Kaiming Initialization 설명 없음

Similar Papers 제목 키워드 기반

Progressive Weight Pruning of Deep Neural Networks using ADMM

2018-10-17 · ICLR 2019 5 · Shaokai Ye, Tianyun Zhang, Kaiqi Zhang, Jiayu Li 외

Deep neural networks (DNNs) although achieving human-level performance in many domains, have very large model size that hinders their broader applications on edge computing devices. Extensive research work have been cond…

Edge-computingModel Compression

Progressive DNN Compression: A Key to Achieve Ultra-High Weight Pruning and Quantization Rates using ADMM

2019-03-23 · Shaokai Ye, Xiaoyu Feng, Tianyun Zhang, Xiaolong Ma 외

Weight pruning and weight quantization are two important categories of DNN model compression. Prior work on these techniques are mainly based on heuristics. A recent work developed a systematic frame-work of DNN weight p…

Model CompressionQuantization

Systematic Weight Pruning of DNNs using Alternating Direction Method of Multipliers

2018-02-15 · Tianyun Zhang, Shaokai Ye, Yi-Peng Zhang, Yanzhi Wang 외

We present a systematic weight pruning framework of deep neural networks (DNNs) using the alternating direction method of multipliers (ADMM). We first formulate the weight pruning problem of DNNs as a constrained nonconv…

Computational Efficiency

Non-Structured DNN Weight Pruning -- Is It Beneficial in Any Platform?

2019-07-03 · Xiaolong Ma, Sheng Lin, Shaokai Ye, Zhezhi He 외

Large deep neural network (DNN) models pose the key challenge to energy efficiency due to the significantly higher energy consumption of off-chip DRAM accesses than arithmetic or SRAM operations. It motivates the intensi…

Model CompressionQuantization

ADMM-NN: An Algorithm-Hardware Co-Design Framework of DNNs Using Alternating Direction Method of Multipliers

2018-12-31 · Ao Ren, Tianyun Zhang, Shaokai Ye, Jiayu Li 외

To facilitate efficient embedded and hardware implementations of deep neural networks (DNNs), two important categories of DNN model compression techniques: weight pruning and weight quantization are investigated. The for…

Model CompressionQuantization