paper-with-me

Papers

Back-and-Forth prediction for deep tensor compression

2020-02-14 · Hyomin Choi, Robert A. Cohen, Ivan V. Bajic

Recent AI applications such as Collaborative Intelligence with neural networks involve transferring deep feature tensors between various computing devices. This necessitates tensor compression in order to optimize the usage of bandwidth-constrained channels between devices. In this paper we present a prediction scheme called Back-and-Forth (BaF) prediction, developed for deep feature tensors, which allows us to dramatically reduce tensor size and improve its compressibility. Our experiments with a state-of-the-art object detector demonstrate that the proposed method allows us to significantly reduce the number of bits needed for compressing feature tensors extracted from deep within the model, with negligible degradation of the detection performance and without requiring any retraining of the network weights. We achieve a 62% and 75% reduction in tensor size while keeping the loss in accuracy of the network to less than 1% and 2%, respectively.

📄 PDF Abstract BibTeX arXiv:2002.07036

Code (0)

등록된 구현이 없습니다.

Tasks

Prediction

Similar Papers 제목 키워드 기반

Compression and Interpretability of Deep Neural Networks via Tucker Tensor Layer: From First Principles to Tensor Valued Back-Propagation

2019-03-14 · Giuseppe G. Calvi, Ahmad Moniri, Mahmoud Mahfouz, Qibin Zhao 외

This work aims to help resolve the two main stumbling blocks in the application of Deep Neural Networks (DNNs), that is, the exceedingly large number of trainable parameters and their physical interpretability. This is a…

Tensorial Neural Networks: Generalization of Neural Networks and Application to Model Compression

2018-05-25 · Jiahao Su, Jingling Li, Bobby Bhattacharjee, Furong Huang

We propose tensorial neural networks (TNNs), a generalization of existing neural networks by extending tensor operations on low order operands to those on high order ones. The problem of parameter learning is challenging…

Model Compressiontensor algebraTensor Decomposition

Novel Factorization Strategies for Higher Order Tensors: Implications for Compression and Recovery of Multi-linear Data

2013-07-02 · Zemin Zhang, Gregory Ely, Shuchin Aeron, Ning Hao 외

In this paper we propose novel methods for compression and recovery of multilinear data under limited sampling. We exploit the recently proposed tensor- Singular Value Decomposition (t-SVD)[1], which is a group theoretic…

Data CompressionTensor Decomposition

A Practical Tensor-Network Compression Pipeline for Production-Scale Large Language Models

2026-02-02 · Sergii Kozyrev, Davyd Maiboroda arxiv

Large language models are limited in deployment by GPU memory and inference latency. We present Minima, a production compression pipeline that learns where and how to structurally compress a Transformer and turns that co…

Tensor Shape Search for Optimum Data Compression

2022-05-21 · Ryan Solgi, Zichang He, William Jiahua Liang, Zheng Zhang

Various tensor decomposition methods have been proposed for data compression. In real world applications of the tensor decomposition, selecting the tensor shape for the given data poses a challenge and the shape of the t…

Data CompressionTensor Decomposition