paper-with-me

Papers

Model compression as constrained optimization, with application to neural nets. Part V: combining compressions

2021-07-09 · Miguel Á. Carreira-Perpiñán, Yerlan Idelbayev

Model compression is generally performed by using quantization, low-rank approximation or pruning, for which various algorithms have been researched in recent years. One fundamental question is: what types of compression work better for a given model? Or even better: can we improve by combining compressions in a suitable way? We formulate this generally as a problem of optimizing the loss but where the weights are constrained to equal an additive combination of separately compressed parts; and we give an algorithm to learn the corresponding parts' parameters. Experimentally with deep neural nets, we observe that 1) we can find significantly better models in the error-compression space, indicating that different compression types have complementary benefits, and 2) the best type of combination depends exquisitely on the type of neural net. For example, we can compress ResNets and AlexNet using only 1 bit per weight without error degradation at the cost of adding a few floating point weights. However, VGG nets can be better compressed by combining low-rank with a few floating point weights.

📄 PDF Abstract BibTeX arXiv:2107.04380

Code (1)

UCMerced-ML/LC-model-compression 공식 구현 pytorch

Tasks

Additive modelsLow-rank compressionModel CompressionNetwork PruningQuantization

Methods 이 논문이 사용한 방법론

Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Model compression as constrained optimization, with application to neural nets. Part I: general framework

2017-07-05 · Miguel Á. Carreira-Perpiñán

Compressing neural nets is an active research problem, given the large size of state-of-the-art nets for tasks such as object recognition, and the computational limits imposed by mobile devices. We give a general formula…

Model CompressionObject RecognitionQuantization

Model compression as constrained optimization, with application to neural nets. Part II: quantization

2017-07-13 · Miguel Á. Carreira-Perpiñán, Yerlan Idelbayev

We consider the problem of deep neural net compression by quantization: given a large, reference net, we want to quantize its real-valued weights using a codebook with $K$ entries so that the training loss of the quantiz…

BinarizationModel CompressionQuantization

EAST: Encoding-Aware Sparse Training for Deep Memory Compression of ConvNets

2019-12-20 · Matteo Grimaldi, Valentino Peluso, Andrea Calimera

The implementation of Deep Convolutional Neural Networks (ConvNets) on tiny end-nodes with limited non-volatile memory space calls for smart compression strategies capable of shrinking the footprint yet preserving predic…

Quantization

Wide Compression: Tensor Ring Nets

2018-02-25 · CVPR 2018 6 · Wenqi Wang, Yifan Sun, Brian Eriksson, Wenlin Wang 외

Deep neural networks have demonstrated state-of-the-art performance in a variety of real-world applications. In order to obtain performance gains, these networks have grown larger and deeper, containing millions or even …

image-classificationImage Classification

Constrained Deep Learning using Conditional Gradient and Applications in Computer Vision

2018-03-17 · Sathya N. Ravi, Tuan Dinh, Vishnu Sai Rao Lokhande, Vikas Singh

A number of results have recently demonstrated the benefits of incorporating various constraints when training deep architectures in vision and machine learning. The advantages range from guarantees for statistical gener…

Image Inpainting