paper-with-me

홈 › Papers

Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition

2021-07-23 · NeurIPS 2021 12 · Lucas Liebenwein, Alaa Maalouf, Oren Gal, Dan Feldman, Daniela Rus

We present a novel global compression framework for deep neural networks that automatically analyzes each layer to identify the optimal per-layer compression ratio, while simultaneously achieving the desired overall compression. Our algorithm hinges on the idea of compressing each convolutional (or fully-connected) layer by slicing its channels into multiple groups and decomposing each group via low-rank decomposition. At the core of our algorithm is the derivation of layer-wise error bounds from the Eckart Young Mirsky theorem. We then leverage these bounds to frame the compression problem as an optimization problem where we wish to minimize the maximum compression error across layers and propose an efficient algorithm towards a solution. Our experiments indicate that our method outperforms existing low-rank compression approaches across a wide range of networks and data sets. We believe that our results open up new avenues for future research into the global performance-size trade-offs of modern neural networks. Our code is available at https://github.com/lucaslie/torchprune.

📄 PDF Abstract BibTeX arXiv:2107.11442

Code (2)

lucaslie/torchprune 공식 구현 pytorch
lucaslie/provable_pruning pytorch

Tasks

Low-rank compression

Similar Papers 제목 키워드 기반

Low-Rank Matrix Approximation for Neural Network Compression

2025-04-25 · Kalyan Cherukuri, Aarav Lala

Deep Neural Networks (DNNs) have encountered an emerging deployment challenge due to large and expensive memory and computation requirements. In this paper, we present a new Adaptive-Rank Singular Value Decomposition (AR…

Model CompressionNeural Network Compression

MoE-I$^2$: Compressing Mixture of Experts Models through Inter-Expert Pruning and Intra-Expert Low-Rank Decomposition

2024-11-01 · Cheng Yang, Yang Sui, Jinqi Xiao, Lingyi Huang 외

The emergence of Mixture of Experts (MoE) LLMs has significantly advanced the development of language models. Compared to traditional LLMs, MoE LLMs outperform traditional LLMs by achieving higher performance with consid…

Mixture-of-Experts

Determining Layer-wise Sparsity for Large Language Models Through a Theoretical Perspective

2025-02-20 · Weizhong Huang, Yuxin Zhang, Xiawu Zheng, Fei Chao 외

In this paper, we address the challenge of determining the layer-wise sparsity rates of large language models (LLMs) through a theoretical perspective. Specifically, we identify a critical issue of ''$\textbf{reconstruct…

CPUGPU

Compressing Facial Makeup Transfer Networks by Collaborative Distillation and Kernel Decomposition

2020-09-16 · Bianjiang Yang, Zi Hui, Haoji Hu, Xinyi Hu 외

Although the facial makeup transfer network has achieved high-quality performance in generating perceptually pleasing makeup images, its capability is still restricted by the massive computation and storage of the networ…

DecoderFacial Makeup Transfer

FALCON: Lightweight and Accurate Convolution

2019-09-25 · Jun-Gi Jang, Chun Quan, Hyun Dong Lee, U Kang

How can we efficiently compress Convolutional Neural Network (CNN) while retaining their accuracy on classification tasks? Depthwise Separable Convolution (DSConv), which replaces a standard convolution with a depthwise …

Tensor Decomposition