Towards Optimal Compression: Joint Pruning and Quantization

• URL: http://arxiv.org/abs/2302.07612v2
• Date: Sun, 11 Jun 2023 10:01:07 GMT
• Title: Towards Optimal Compression: Joint Pruning and Quantization
• Authors: Ben Zandonati, Glenn Bucagu, Adrian Alan Pol, Maurizio Pierini, Olya Sirkin, Tal Kopetz
• Abstract summary: This paper introduces FITCompress, a novel method integrating layer-wise mixed-precision quantization and unstructured pruning. Experiments on computer vision and natural language processing benchmarks demonstrate that our proposed approach achieves a superior compression-performance trade-off.
• Score: 1.191194620421783
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Model compression is instrumental in optimizing deep neural network inference on resource-constrained hardware. The prevailing methods for network compression, namely quantization and pruning, have been shown to enhance efficiency at the cost of performance. Determining the most effective quantization and pruning strategies for individual layers and parameters remains a challenging problem, often requiring computationally expensive and ad hoc numerical optimization techniques. This paper introduces FITCompress, a novel method integrating layer-wise mixed-precision quantization and unstructured pruning using a unified heuristic approach. By leveraging the Fisher Information Metric and path planning through compression space, FITCompress optimally selects a combination of pruning mask and mixed-precision quantization configuration for a given pre-trained model and compression constraint. Experiments on computer vision and natural language processing benchmarks demonstrate that our proposed approach achieves a superior compression-performance trade-off compared to existing state-of-the-art methods. FITCompress stands out for its principled derivation, making it versatile across tasks and network architectures, and represents a step towards achieving optimal compression for neural networks.

Related papers

• Quantization Aware Factorization for Deep Neural Network Compression [20.04951101799232]
  decomposition of convolutional and fully-connected layers is an effective way to reduce parameters and FLOP in neural networks. A conventional post-training quantization approach applied to networks with weights yields a drop in accuracy. This motivated us to develop an algorithm that finds decomposed approximation directly with quantized factors.
  arXiv  Detail & Related papers  (2023-08-08T21:38:02Z)
• Learning Accurate Performance Predictors for Ultrafast Automated Model Compression [86.22294249097203]
  We propose an ultrafast automated model compression framework called SeerNet for flexible network deployment. Our method achieves competitive accuracy-complexity trade-offs with significant reduction of the search cost.
  arXiv  Detail & Related papers  (2023-04-13T10:52:49Z)
• Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning [29.284147465251685]
  We introduce a new compression framework which covers both weight pruning and quantization in a unified setting. We show that it can improve significantly upon the compression-accuracy trade-offs of existing post-training methods.
  arXiv  Detail & Related papers  (2022-08-24T14:33:35Z)
• Efficient Micro-Structured Weight Unification and Pruning for Neural Network Compression [56.83861738731913]
  Deep Neural Network (DNN) models are essential for practical applications, especially for resource limited devices. Previous unstructured or structured weight pruning methods can hardly truly accelerate inference. We propose a generalized weight unification framework at a hardware compatible micro-structured level to achieve high amount of compression and acceleration.
  arXiv  Detail & Related papers  (2021-06-15T17:22:59Z)
• Dynamic Probabilistic Pruning: A general framework for hardware-constrained pruning at different granularities [80.06422693778141]
  We propose a flexible new pruning mechanism that facilitates pruning at different granularities (weights, kernels, filters/feature maps) We refer to this algorithm as Dynamic Probabilistic Pruning (DPP) We show that DPP achieves competitive compression rates and classification accuracy when pruning common deep learning models trained on different benchmark datasets for image classification.
  arXiv  Detail & Related papers  (2021-05-26T17:01:52Z)
• Neural Network Compression Via Sparse Optimization [23.184290795230897]
  We propose a model compression framework based on the recent progress on sparse optimization. We achieve up to 7.2 and 2.9 times FLOPs reduction with the same level of evaluation of accuracy on VGG16 for CIFAR10 and ResNet50 for ImageNet.
  arXiv  Detail & Related papers  (2020-11-10T03:03:55Z)
• ALF: Autoencoder-based Low-rank Filter-sharing for Efficient Convolutional Neural Networks [63.91384986073851]
  We propose the autoencoder-based low-rank filter-sharing technique technique (ALF) ALF shows a reduction of 70% in network parameters, 61% in operations and 41% in execution time, with minimal loss in accuracy.
  arXiv  Detail & Related papers  (2020-07-27T09:01:22Z)
• Structured Sparsification with Joint Optimization of Group Convolution and Channel Shuffle [117.95823660228537]
  We propose a novel structured sparsification method for efficient network compression. The proposed method automatically induces structured sparsity on the convolutional weights. We also address the problem of inter-group communication with a learnable channel shuffle mechanism.
  arXiv  Detail & Related papers  (2020-02-19T12:03:10Z)
• End-to-End Facial Deep Learning Feature Compression with Teacher-Student Enhancement [57.18801093608717]
  We propose a novel end-to-end feature compression scheme by leveraging the representation and learning capability of deep neural networks. In particular, the extracted features are compactly coded in an end-to-end manner by optimizing the rate-distortion cost. We verify the effectiveness of the proposed model with the facial feature, and experimental results reveal better compression performance in terms of rate-accuracy.
  arXiv  Detail & Related papers  (2020-02-10T10:08:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.