Compressing RNNs for IoT devices by 15-38x using Kronecker Products

7 June 2019

Papers citing "Compressing RNNs for IoT devices by 15-38x using Kronecker Products"

21 / 21 papers shown

Title
Efficient Zero-Order Federated Finetuning of Language Models for Resource-Constrained Devices Mohamed Aboelenien Ahmed Kilian Pfeiffer R. Khalili Heba Khdr J. Henkel FedML 94 0 0 17 Feb 2025
DiffuseKronA: A Parameter Efficient Fine-tuning Method for Personalized Diffusion Models Shyam Marjit Harshit Singh Nityanand Mathur Sayak Paul Chia-Mu Yu Pin-Yu Chen DiffM 47 6 0 27 Feb 2024
TQCompressor: improving tensor decomposition methods in neural networks via permutations V. Abronin A. Naumov D. Mazur D. Bystrov K. Tsarova Ar. Melnikov Ivan Oseledets S. Dolgov R. Brasher M. Perelshtein 28 6 0 29 Jan 2024
From array algebra to energy efficiency on GPUs: Data and hardware shapes with dimension-lifting to optimize memory-processor layouts L. Mullin 24 0 0 19 Jun 2023
Low Rank Optimization for Efficient Deep Learning: Making A Balance between Compact Architecture and Fast Training Xinwei Ou Zhangxin Chen Ce Zhu Yipeng Liu 36 4 0 22 Mar 2023
SeKron: A Decomposition Method Supporting Many Factorization Structures Marawan Gamal Abdel Hameed A. Mosleh Marzieh S. Tahaei V. Nia 29 1 0 12 Oct 2022
CoCoFL: Communication- and Computation-Aware Federated Learning via Partial NN Freezing and Quantization Kilian Pfeiffer Martin Rapp R. Khalili J. Henkel FedML 13 11 0 10 Mar 2022
DISTREAL: Distributed Resource-Aware Learning in Heterogeneous Systems Martin Rapp R. Khalili Kilian Pfeiffer J. Henkel 19 18 0 16 Dec 2021
Kronecker Decomposition for GPT Compression Ali Edalati Marzieh S. Tahaei Ahmad Rashid V. Nia J. Clark Mehdi Rezagholizadeh 36 33 0 15 Oct 2021
Convolutional Neural Network Compression through Generalized Kronecker Product Decomposition Marawan Gamal Abdel Hameed Marzieh S. Tahaei A. Mosleh V. Nia 47 25 0 29 Sep 2021
Compacting Deep Neural Networks for Internet of Things: Methods and Applications Ke Zhang Hanbo Ying Hongning Dai Lin Li Yuangyuang Peng Keyi Guo Hongfang Yu 18 38 0 20 Mar 2021
Doping: A technique for efficient compression of LSTM models using sparse structured additive matrices Urmish Thakker P. Whatmough Zhi-Gang Liu Matthew Mattina Jesse G. Beu 16 6 0 14 Feb 2021
Paralinguistic Privacy Protection at the Edge Ranya Aloufi Hamed Haddadi David E. Boyle 17 14 0 04 Nov 2020
Rank and run-time aware compression of NLP Applications Urmish Thakker Jesse G. Beu Dibakar Gope Ganesh S. Dasika Matthew Mattina 16 11 0 06 Oct 2020
High Throughput Matrix-Matrix Multiplication between Asymmetric Bit-Width Operands Dibakar Gope Jesse G. Beu Matthew Mattina 20 4 0 03 Aug 2020
Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers Zhuohan Li Eric Wallace Sheng Shen Kevin Lin Kurt Keutzer Dan Klein Joseph E. Gonzalez 14 148 0 26 Feb 2020
Federated Learning for Resource-Constrained IoT Devices: Panoramas and State-of-the-art Ahmed Imteaj Urmish Thakker Shiqiang Wang Jian Li M. Amini 8 59 0 25 Feb 2020
Compressing Language Models using Doped Kronecker Products Urmish Thakker Paul Whatamough Zhi-Gang Liu Matthew Mattina Jesse G. Beu 6 9 0 24 Jan 2020
DARB: A Density-Aware Regular-Block Pruning for Deep Neural Networks Ao Ren Tao Zhang Yuhao Wang Sheng Lin Peiyan Dong Yen-kuang Chen Yuan Xie Yanzhi Wang 20 11 0 19 Nov 2019
Ternary MobileNets via Per-Layer Hybrid Filter Banks Dibakar Gope Jesse G. Beu Urmish Thakker Matthew Mattina MQ 32 15 0 04 Nov 2019
Run-Time Efficient RNN Compression for Inference on Edge Devices Urmish Thakker Jesse G. Beu Dibakar Gope Ganesh S. Dasika Matthew Mattina 11 18 0 12 Jun 2019