Doping: A technique for efficient compression of LSTM models using
sparse structured additive matrices

Doping: A technique for efficient compression of LSTM models using sparse structured additive matrices

Conference on Machine Learning and Systems (MLSys), 2021

14 February 2021

Matthew Mattina

ArXiv (abs)PDF HTML

Papers citing "Doping: A technique for efficient compression of LSTM models using sparse structured additive matrices"

4 / 4 papers shown

Title
Fast Kronecker Matrix-Matrix Multiplication on GPUs Abhinav Jangda Mohit Yadav 249 4 0 18 Jan 2024
Sparse-IFT: Sparse Iso-FLOP Transformations for Maximizing Training EfficiencyInternational Conference on Machine Learning (ICML), 2023 Vithursan Thangarasa Shreyas Saxena Abhay Gupta Sean Lie 404 6 0 21 Mar 2023
Machine Learning for Microcontroller-Class Hardware: A ReviewIEEE Sensors Journal (IEEE Sens. J.), 2022 Swapnil Sayan Saha S. Sandha Mani B. Srivastava 427 168 0 29 May 2022
S2TA: Exploiting Structured Sparsity for Energy-Efficient Mobile CNN AccelerationInternational Symposium on High-Performance Computer Architecture (HPCA), 2021 Zhi-Gang Liu P. Whatmough Yuhao Zhu Matthew Mattina MQ 170 99 0 16 Jul 2021