paper-with-me

Papers

Accelerating the Low-Rank Decomposed Models

2024-07-24 · Habib Hajimolahoseini, Walid Ahmed, Austin Wen, Yang Liu

Tensor decomposition is a mathematically supported technique for data compression. It consists of applying some kind of a Low Rank Decomposition technique on the tensors or matrices in order to reduce the redundancy of the data. However, it is not a popular technique for compressing the AI models duo to the high number of new layers added to the architecture after decomposition. Although the number of parameters could shrink significantly, it could result in the model be more than twice deeper which could add some latency to the training or inference. In this paper, we present a comprehensive study about how to modify low rank decomposition technique in AI models so that we could benefit from both high accuracy and low memory consumption as well as speeding up the training and inference

📄 PDF Abstract BibTeX arXiv:2407.20266

Code (0)

등록된 구현이 없습니다.

Tasks

Data CompressionTensor Decomposition

Similar Papers 제목 키워드 기반

Training Acceleration of Low-Rank Decomposed Networks using Sequential Freezing and Rank Quantization

2023-09-07 · Habib Hajimolahoseini, Walid Ahmed, Yang Liu

Low Rank Decomposition (LRD) is a model compression technique applied to the weight tensors of deep learning models in order to reduce the number of trainable parameters and computational complexity. However, due to high…

Model CompressionQuantization

Automatic Rank Selection for High-Speed Convolutional Neural Network

2018-06-28 · Hyeji Kim, Chong-Min Kyung

Low-rank decomposition plays a central role in accelerating convolutional neural network (CNN), and the rank of decomposed kernel-tensor is a key parameter that determines the complexity and accuracy of a neural network.…

Combinatorial OptimizationVocal Bursts Intensity Prediction

Accelerating Training using Tensor Decomposition

2019-09-10 · Mostafa Elhoushi, Ye Henry Tian, Zihao Chen, Farhan Shafiq 외

Tensor decomposition is one of the well-known approaches to reduce the latency time and number of parameters of a pre-trained model. However, in this paper, we propose an approach to use tensor decomposition to reduce tr…

CPUGPUTensor Decomposition

UniRank: Unified Rank Allocation for Low-Rank LLM Compression

2026-06-20 · Chao Han, Haozhe Hu, Fei Ma, Wei Zhang 외 arxiv

Low-rank decomposition serves as a promising compression paradigm for large language models, however, rank allocation remains challenging: manual rules lack generalizability, and learning-based approaches incur heavy com…

Learning Low-Rank Approximation for CNNs

2019-05-24 · Dongsoo Lee, Se Jung Kwon, Byeongwook Kim, Gu-Yeon Wei

Low-rank approximation is an effective model compression technique to not only reduce parameter storage requirements, but to also reduce computations. For convolutional neural networks (CNNs), however, well-known low-ran…

Model Compression