Compressed Deep Networks: Goodbye SVD, Hello Robust Low-Rank Approximation

Murad Tukan, Alaa Maalouf, Matan Weksler +1

A common technique for compressing a neural network is to compute the $k$-rank ${\ell }_2$ approximation $A_{k,2}$ of the matrix $A\in {\mathbb{R}}^{n\times d}$ that corresponds to a ful…