No Fine-Tuning, No Cry: Robust SVD for Compressing Deep Networks

No Fine-Tuning, No Cry: Robust SVD for Compressing Deep Networks

A common technique for compressing a neural network is to compute the <i>k</i>-rank <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>ℓ</mi><mn>2</mn></msub><...

Full description

Bibliographic Details
Main Authors: Murad Tukan, Alaa Maalouf, Matan Weksler, Dan Feldman
Format: Article
Language:English
Published: MDPI AG 2021-08-01
Series:Sensors
Subjects:
matrix factorization
neural networks compression
robust low rank approximation
Löwner ellipsoid
Online Access:https://www.mdpi.com/1424-8220/21/16/5599

Internet

https://www.mdpi.com/1424-8220/21/16/5599

Similar Items