paper-with-me

홈 › Papers

Towards Optimal Compression: Joint Pruning and Quantization

2023-02-15 · Ben Zandonati, Glenn Bucagu, Adrian Alan Pol, Maurizio Pierini, Olya Sirkin, Tal Kopetz

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.

📄 PDF Abstract BibTeX arXiv:2302.07612

Code (0)

등록된 구현이 없습니다.

Tasks

Model CompressionNeural Architecture SearchQuantization

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Pruning 설명 없음
HOC 설명 없음
Adam 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
WordPiece 설명 없음
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 $x$…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

Automated Model Compression by Jointly Applied Pruning and Quantization

2020-11-12 · Wenting Tang, Xingxing Wei, Bo Li

In the traditional deep compression framework, iteratively performing network pruning and quantization can reduce the model size and computation cost to meet the deployment requirements. However, such a step-wise applica…

AutoMLModel CompressionNetwork Pruningobject-detection+2

Differentiable Joint Pruning and Quantization for Hardware Efficiency

2020-07-20 · ECCV 2020 8 · Ying Wang, Yadong Lu, Tijmen Blankevoort

We present a differentiable joint pruning and quantization (DJPQ) scheme. We frame neural network compression as a joint gradient-based optimization problem, trading off between model pruning and quantization automatical…

Neural Network CompressionQuantization

Single-path Bit Sharing for Automatic Loss-aware Model Compression

2021-01-13 · Jing Liu, Bohan Zhuang, Peng Chen, Chunhua Shen 외

Network pruning and quantization are proven to be effective ways for deep model compression. To obtain a highly compact model, most methods first perform network pruning and then conduct network quantization based on the…

Model CompressionNetwork PruningQuantization

Optimal Brain Restoration for Joint Quantization and Sparsification of LLMs

2025-09-14 · Hang Guo, Yawei Li, Luca Benini arxiv

Recent advances in Large Language Model (LLM) compression, such as quantization and pruning, have achieved notable success. However, as these techniques gradually approach their respective limits, relying on a single met…

CoDeQ: End-to-End Joint Model Compression with Dead-Zone Quantizer for High-Sparsity and Low-Precision Networks

2025-12-15 · Jonathan Wenshøj, Tong Chen, Bob Pepin, Raghavendra Selvan arxiv

While joint pruning--quantization is theoretically superior to sequential application, current joint methods rely on auxiliary procedures outside the training loop for finding compression parameters. This reliance adds e…

Model Compression