Timezone: »

What if Neural Networks had SVDs?
Alexander Mathiasen · Frederik Hvilshøj · Jakob Rødsgaard Jørgensen · Anshul Nasery · Davide Mottin

Wed Dec 09 09:00 AM -- 11:00 AM (PST) @ 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.

Author Information

Alexander Mathiasen (Aarhus University)
Frederik Hvilshøj (Aarhus University)
Jakob Rødsgaard Jørgensen (Aarhus University)
Anshul Nasery (Indian Institute of Technology)
Davide Mottin (Aarhus University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors