paper-with-me

Papers

Layer-Wise Data-Free CNN Compression

2020-11-18 · Maxwell Horton, Yanzi Jin, Ali Farhadi, Mohammad Rastegari

We present a computationally efficient method for compressing a trained neural network without using real data. We break the problem of data-free network compression into independent layer-wise compressions. We show how to efficiently generate layer-wise training data using only a pretrained network. We use this data to perform independent layer-wise compressions on the pretrained network. We also show how to precondition the network to improve the accuracy of our layer-wise compression method. We present results for layer-wise compression using quantization and pruning. When quantizing, we compress with higher accuracy than related works while using orders of magnitude less compute. When compressing MobileNetV2 and evaluating on ImageNet, our method outperforms existing methods for quantization at all bit-widths, achieving a $+0.34\%$ improvement in $8$-bit quantization, and a stronger improvement at lower bit-widths (up to a $+28.50\%$ improvement at $5$ bits). When pruning, we outperform baselines of a similar compute envelope, achieving $1.5$ times the sparsity rate at the same accuracy. We also show how to combine our efficient method with high-compute generative methods to improve upon their results.

📄 PDF Abstract BibTeX arXiv:2011.09058

Code (0)

등록된 구현이 없습니다.

Tasks

Quantization

Methods 이 논문이 사용한 방법론

Tether Customer Service Number +1-833-534-1729 설명 없음
Sigmoid Activation 설명 없음
Inverted Residual Block 설명 없음
(FiLe@Against@Claim)How do I file a claim against Expedia? How do I file a claim against Expedia? How Do I File a Claim Against Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Fast Help &…
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 $x$…
Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…
Batch Normalization 설명 없음
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…

Similar Papers 제목 키워드 기반

Globally optimized SVD compression of LLMs via Fermi-function-based rank selection and gauge fixing

2025-11-26 · Roman Rausch, David Jansen, Sukhbinder Singh, Román Orús arxiv

Large Language Models (LLMs) are very demanding in terms of their computational resources. Low-rank decompositions of LLM weights, e.g. via Singular Value Decomposition (SVD), is a promising approach for LLM compression,…

EvoCut: Multi-Layer Evolution-Aware Visual Token Compression for Efficient Large Vision-Language Models

2026-06-01 · Hongyu Lu, Feng Zhang, Wenwei Jin, Huanling Hu 외 arxiv

Large vision-language models (LVLMs) achieve strong performance on image and video understanding tasks, but their inference efficiency is constrained by the large number of visual tokens produced by vision encoders. Most…

Breaking the Compression Ceiling: Data-Free Pipeline for Ultra-Efficient Delta Compression

2025-05-19 · Xiaohui Wang, Peng Ye, Chenyu Huang, Shenghe Zheng 외

With the rise of the fine-tuned--pretrained paradigm, storing numerous fine-tuned models for multi-tasking creates significant storage overhead. Delta compression alleviates this by storing only the pretrained model and …

Pushing the Limits of Large Language Model Quantization via the Linearity Theorem

2024-11-26 · Vladimir Malinovskii, Andrei Panferov, Ivan Ilin, Han Guo 외

Quantizing large language models has become a standard way to reduce their memory and computational costs. Typically, existing methods focus on breaking down the problem into individual layer-wise sub-problems, and minim…

GPULanguage ModelingLanguage ModellingLarge Language Model+1

Swift-SVD: Theoretical Optimality Meets Practical Efficiency in Low-Rank LLM Compression

2026-04-02 · Ruoling Qi, Yirui Liu, Xuaner Wu, Xiangyu Wang 외 arxiv

The deployment of Large Language Models is constrained by the memory and bandwidth demands of static weights and dynamic Key-Value cache. SVD-based compression provides a hardware-friendly solution to reduce these costs.…