papers AI Learner
The Github is limit! Click to go to the new site.

MUSCO: Multi-Stage Compression of neural networks

2019-05-13
Julia Gusak, Maksym Kholyavchenko, Evgeny Ponomarev, Larisa Markeeva, Ivan Oseledets, Andrzej Cichocki

Abstract

The low-rank tensor approximation is very promising for the compression of deep neural networks. We propose a new simple and efficient iterative approach, which alternates low-rank factorization with a smart rank selection and fine-tuning. We demonstrate the efficiency of our method comparing to non-iterative ones. Our approach improves the compression rate while maintaining the accuracy for a variety of tasks.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1903.09973

PDF

http://arxiv.org/pdf/1903.09973


Similar Posts

Comments