Skip to yearly menu bar Skip to main content


What if Neural Networks had SVDs?

Alexander Mathiasen · Frederik Hvilshøj · Jakob Rødsgaard Jørgensen · Anshul Nasery · Davide Mottin

Poster Session 3 #746


Various Neural Networks employ time-consuming matrix operations like matrix inversion. Many such matrix operations are faster to compute given the Singular Value Decomposition (SVD). Techniques from (Zhang et al., 2018; Mhammedi et al., 2017) allow using the SVD in Neural Networks without computing it. In theory, the techniques can speed up matrix operations, however, in practice, they are not fast enough. We present an algorithm that is fast enough to speed up several matrix operations. The algorithm increases the degree of parallelism of an underlying matrix multiplication H*X where H is an orthogonal matrix represented by a product of Householder matrices.

Chat is not available.